--- title: Agents url: https://platform.claude.com/docs/en/api/cli/beta/agents --- # Agents ## Create Agent `$ ant beta:agents create` **POST** `/v1/agents` Create Agent ### Parameters - `--model: BetaManagedAgentsModel or BetaManagedAgentsModelConfigParams` Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=cli#latest-models-comparison), e.g. `claude-opus-5-5`, or a `model_config` object for additional configuration control - `--name: string` Human-readable name for the agent. minLength: 1, maxLength: 256 - `--description: optional string` Description of what the agent does. maxLength: 2048 - `--execution-identity: optional BetaManagedAgentsAWSRoleExecutionIdentityParams or BetaManagedAgentsServiceAccountExecutionIdentityParams` Execution principal for runs of this agent. Omitting it, sending null, or sending `{"type": "service_account"}` stores the default. - `--mcp-server: optional array of BetaManagedAgentsURLMCPServerParams` MCP servers this agent connects to. Maximum 20. Names must be unique within the array. Every server must be referenced by an `mcp_toolset` in `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector?sdk_languages=cli). - `--metadata: optional map[string]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `--multiagent: optional BetaManagedAgentsMultiagentCoordinatorParams or BetaManagedAgentsMultiagent20261001Params` Multiagent orchestration configuration. - `--skill: optional array of BetaManagedAgentsSkillParams` Skills available to the agent. - `--system: optional string` System prompt for the agent. maxLength: 100000 - `--tool: optional array of BetaManagedAgentsAgentToolset20260401Params or BetaManagedAgentsMCPToolsetParams or BetaManagedAgentsCustomToolParams` Tool configurations available to the agent. Maximum of 256 tools across all toolsets allowed. - `--beta: optional array of AnthropicBeta` (header parameter) This endpoint is in beta: requests must send `managed-agents-2026-04-01` in this header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `beta_managed_agents_agent: object` A Managed Agents `agent`. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 ### Example ```bash ant beta:agents create \ --api-key my-anthropic-api-key \ --model claude-opus-5-5 \ --name 'My First Agent' ``` #### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "execution_identity": { "type": "service_account" }, "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ## List Agents `$ ant beta:agents list` **GET** `/v1/agents` List Agents ### Parameters - `--created-at-gte: optional string` (query parameter) Return agents created at or after this time (inclusive). format: date-time - `--created-at-lte: optional string` (query parameter) Return agents created at or before this time (inclusive). format: date-time - `--include-archived: optional boolean` (query parameter) Include archived agents in results. Defaults to false. - `--limit: optional number` (query parameter) Maximum results per page. Default 20, maximum 100. format: int32 - `--page: optional string` (query parameter) Opaque pagination cursor from a previous response. - `--beta: optional array of AnthropicBeta` (header parameter) This endpoint is in beta: requests must send `managed-agents-2026-04-01` in this header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `BetaManagedAgentsListAgents: object` Paginated list of agents. - `data: array of BetaManagedAgentsAgent` List of agents. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 - `next_page: optional string` Opaque cursor for the next page. Null when no more results. ### Example ```bash ant beta:agents list \ --api-key my-anthropic-api-key ``` #### Response (200) ```json { "data": [ { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "execution_identity": { "type": "service_account" }, "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ], "next_page": "next_page" } ``` ## Get Agent `$ ant beta:agents retrieve` **GET** `/v1/agents/{agent_id}` Get Agent ### Parameters - `--agent-id: string` (path parameter) Unique identifier of the agent to retrieve. - `--version: optional number` (query parameter) Agent version. Omit for the most recent version. Must be at least 1 if specified. format: int32 - `--beta: optional array of AnthropicBeta` (header parameter) This endpoint is in beta: requests must send `managed-agents-2026-04-01` in this header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `beta_managed_agents_agent: object` A Managed Agents `agent`. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 ### Example ```bash ant beta:agents retrieve \ --api-key my-anthropic-api-key \ --agent-id agent_011CZkYpogX7uDKUyvBTophP ``` #### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "execution_identity": { "type": "service_account" }, "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ## Update Agent `$ ant beta:agents update` **POST** `/v1/agents/{agent_id}` Update Agent ### Parameters - `--agent-id: string` (path parameter) Unique identifier of the agent to update. - `--description: optional string` Description. Omit to preserve; send empty string or null to clear. maxLength: 2048 - `--execution-identity: optional BetaManagedAgentsAWSRoleExecutionIdentityParams or BetaManagedAgentsServiceAccountExecutionIdentityParams` Execution principal for runs of this agent. Full replacement. Omit to preserve; send null or `{"type": "service_account"}` to restore the default. - `--mcp-server: optional array of BetaManagedAgentsURLMCPServerParams` MCP servers. Full replacement. Omit to preserve; send empty array or `null` to clear. Names must be unique. Maximum 20. Every server must be referenced by an `mcp_toolset` in the agent's resulting `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector?sdk_languages=cli). - `--metadata: optional map[string]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve. The stored bag is limited to 16 keys (up to 64 chars each) with values up to 512 chars. - `--model: optional BetaManagedAgentsModel or BetaManagedAgentsModelConfigParams` Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=cli#latest-models-comparison), e.g. `claude-opus-5-5`, or a `model_config` object for additional configuration control. Omit to preserve. Cannot be cleared. - `--multiagent: optional BetaManagedAgentsMultiagentCoordinatorParams or BetaManagedAgentsMultiagent20261001Params` Multiagent orchestration configuration. Full replacement. Omit to preserve; send null to clear. - `--name: optional string` Human-readable name. Must be non-empty. Omit to preserve. Cannot be cleared. maxLength: 256 - `--skill: optional array of BetaManagedAgentsSkillParams` Skills. Full replacement. Omit to preserve; send empty array or null to clear. - `--system: optional string` System prompt. Omit to preserve; send empty string or null to clear. maxLength: 100000 - `--tool: optional array of BetaManagedAgentsAgentToolset20260401Params or BetaManagedAgentsMCPToolsetParams or BetaManagedAgentsCustomToolParams` Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 256 tools across all toolsets allowed. - `--version: optional number` The agent's current version, used to prevent concurrent overwrites. Obtain this value from a create or retrieve response. Must be at least 1 if specified. When supplied, the request fails if it does not match the server's current version; omit to apply the update unconditionally. format: int32 - `--beta: optional array of AnthropicBeta` (header parameter) This endpoint is in beta: requests must send `managed-agents-2026-04-01` in this header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `beta_managed_agents_agent: object` A Managed Agents `agent`. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 ### Example ```bash ant beta:agents update \ --api-key my-anthropic-api-key \ --agent-id agent_011CZkYpogX7uDKUyvBTophP ``` #### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "execution_identity": { "type": "service_account" }, "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ## Archive Agent `$ ant beta:agents archive` **POST** `/v1/agents/{agent_id}/archive` Archive Agent ### Parameters - `--agent-id: string` (path parameter) Unique identifier of the agent to archive. - `--beta: optional array of AnthropicBeta` (header parameter) This endpoint is in beta: requests must send `managed-agents-2026-04-01` in this header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `beta_managed_agents_agent: object` A Managed Agents `agent`. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 ### Example ```bash ant beta:agents archive \ --api-key my-anthropic-api-key \ --agent-id agent_011CZkYpogX7uDKUyvBTophP ``` #### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "execution_identity": { "type": "service_account" }, "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ## Domain types ### Beta Managed Agents Advisor - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. ### Beta Managed Agents Agent - `beta_managed_agents_agent: object` A Managed Agents `agent`. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 ### Beta Managed Agents Agent Reference - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 ### Beta Managed Agents Agent Tool Config - `beta_managed_agents_agent_tool_config: BetaManagedAgentsBashToolConfig or BetaManagedAgentsEditToolConfig or BetaManagedAgentsReadToolConfig or 5 more` Configuration for a specific agent tool. - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 ### Beta Managed Agents Agent Tool Config Params - `beta_managed_agents_agent_tool_config_params: BetaManagedAgentsBashToolConfigParams or BetaManagedAgentsEditToolConfigParams or BetaManagedAgentsReadToolConfigParams or 5 more` Configuration override for a specific tool within a toolset. - `beta_managed_agents_bash_tool_config_params: object` Configuration override for the bash tool. - `type: optional "bash"` - `name: "bash"` Must be "bash". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config_params: object` Configuration override for the edit tool. - `type: optional "edit"` - `name: "edit"` Must be "edit". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config_params: object` Configuration override for the read tool. - `type: optional "read"` - `name: "read"` Must be "read". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config_params: object` Configuration override for the write tool. - `type: optional "write"` - `name: "write"` Must be "write". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config_params: object` Configuration override for the glob tool. - `type: optional "glob"` - `name: "glob"` Must be "glob". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config_params: object` Configuration override for the grep tool. - `type: optional "grep"` - `name: "grep"` Must be "grep". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config_params: object` Configuration override for the web_fetch tool. - `type: optional "web_fetch"` - `name: "web_fetch"` Must be "web_fetch". - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: optional array of string` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: optional number` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: optional object` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `user_input: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceUserInput` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_search_tool_config_params: object` Configuration override for the web_search tool. - `type: optional "web_search"` - `name: "web_search"` Must be "web_search". - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: optional array of string` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 ### Beta Managed Agents Agent Toolset Default Config - `beta_managed_agents_agent_toolset_default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Agent Toolset Default Config Params - `beta_managed_agents_agent_toolset_default_config_params: object` Default configuration for all tools in a toolset. - `enabled: optional boolean` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Agent Toolset20260401 - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. ### Beta Managed Agents Agent Toolset20260401 Bash Input - `beta_managed_agents_agent_toolset20260401_bash_input: object` Input payload for the `bash` tool of the `agent_toolset_20260401` toolset. All fields are optional; a normal invocation supplies `command`, while `restart=true` (with no `command`) reboots the runner-side bash session. - `command: optional string` Shell command to execute. Omit only when `restart` is true. - `restart: optional boolean` When true, restart the persistent bash session instead of running a command. Subsequent calls without `restart` will run against the fresh session. - `timeout_ms: optional number` Per-call timeout in milliseconds. Defaults to the runner-wide tool timeout when omitted or zero. minimum: 0 ### Beta Managed Agents Agent Toolset20260401 Edit Input - `beta_managed_agents_agent_toolset20260401_edit_input: object` Input payload for the `edit` tool. Performs a string replacement in the named file; by default `old_string` must occur exactly once. - `file_path: string` Path of the file to edit. - `new_string: string` Replacement text. - `old_string: string` Substring to find and replace. - `replace_all: optional boolean` When true, replace every occurrence of `old_string` instead of requiring a unique match. ### Beta Managed Agents Agent Toolset20260401 Glob Input - `beta_managed_agents_agent_toolset20260401_glob_input: object` Input payload for the `glob` tool. Returns paths matching a doublestar glob pattern, newest first. - `pattern: string` Doublestar glob pattern (e.g. `**/*.go`). Absolute patterns are only permitted when the runner is configured to allow them. - `path: optional string` Optional directory root to search under. Defaults to the runner's working directory. ### Beta Managed Agents Agent Toolset20260401 Grep Input - `beta_managed_agents_agent_toolset20260401_grep_input: object` Input payload for the `grep` tool. Searches file contents for a regular expression, returning matching lines. - `pattern: string` Regular expression to search for. - `path: optional string` Optional directory root to search under. Defaults to the runner's working directory. ### Beta Managed Agents Agent Toolset20260401 Params - `beta_managed_agents_agent_toolset20260401_params: object` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: "agent_toolset_20260401"` - `configs: optional array of BetaManagedAgentsAgentToolConfigParams` Per-tool configuration overrides. - `beta_managed_agents_bash_tool_config_params: object` Configuration override for the bash tool. - `type: optional "bash"` - `name: "bash"` Must be "bash". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config_params: object` Configuration override for the edit tool. - `type: optional "edit"` - `name: "edit"` Must be "edit". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config_params: object` Configuration override for the read tool. - `type: optional "read"` - `name: "read"` Must be "read". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config_params: object` Configuration override for the write tool. - `type: optional "write"` - `name: "write"` Must be "write". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config_params: object` Configuration override for the glob tool. - `type: optional "glob"` - `name: "glob"` Must be "glob". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config_params: object` Configuration override for the grep tool. - `type: optional "grep"` - `name: "grep"` Must be "grep". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config_params: object` Configuration override for the web_fetch tool. - `type: optional "web_fetch"` - `name: "web_fetch"` Must be "web_fetch". - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: optional array of string` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: optional number` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: optional object` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `user_input: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceUserInput` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_search_tool_config_params: object` Configuration override for the web_search tool. - `type: optional "web_search"` - `name: "web_search"` Must be "web_search". - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: optional array of string` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: optional object` Default configuration applied to all tools in this set. - `enabled: optional boolean` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. ### Beta Managed Agents Agent Toolset20260401 Read Input - `beta_managed_agents_agent_toolset20260401_read_input: object` Input payload for the `read` tool. Reads file contents relative to the runner's working directory (or absolute when the runner permits). - `file_path: string` Path of the file to read. - `view_range: optional array of number` Optional `[start_line, end_line]` 1-indexed inclusive range. When omitted the entire file is returned. `end_line` of 0 or negative means "to end of file". minItems: 2, maxItems: 2 ### Beta Managed Agents Agent Toolset20260401 Write Input - `beta_managed_agents_agent_toolset20260401_write_input: object` Input payload for the `write` tool. Writes (overwriting) the entire file contents. - `content: string` Full file contents to write. - `file_path: string` Path of the file to write. ### Beta Managed Agents Always Allow Policy - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` ### Beta Managed Agents Always Ask Policy - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` ### Beta Managed Agents Anthropic Skill - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` ### Beta Managed Agents Anthropic Skill Params - `beta_managed_agents_anthropic_skill_params: object` An Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` Identifier of the Anthropic skill (e.g., "xlsx"). minLength: 1, maxLength: 64 - `version: optional string` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 ### Beta Managed Agents Auto Policy - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents AWS Role Execution Identity - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. ### Beta Managed Agents AWS Role Execution Identity Params - `beta_managed_agents_aws_role_execution_identity_params: object` An AWS IAM role principal. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN, e.g. "arn:aws:iam::123456789012:role/my-agent-runner". Maximum 2048 characters. maxLength: 2048 ### Beta Managed Agents Bash Tool Config - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Bash Tool Config Params - `beta_managed_agents_bash_tool_config_params: object` Configuration override for the bash tool. - `type: optional "bash"` - `name: "bash"` Must be "bash". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Custom Skill - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` ### Beta Managed Agents Custom Skill Params - `beta_managed_agents_custom_skill_params: object` A user-created custom skill. - `type: "custom"` - `skill_id: string` Tagged ID of the custom skill (e.g., "skill_01XJ5..."). minLength: 1, maxLength: 64 - `version: optional string` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 ### Beta Managed Agents Custom Tool - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` ### Beta Managed Agents Custom Tool Input Schema - `beta_managed_agents_custom_tool_input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` ### Beta Managed Agents Custom Tool Params - `beta_managed_agents_custom_tool_params: object` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event. - `type: "custom"` - `description: string` Description of what the tool does, shown to the agent to help it decide when to use the tool. minLength: 1 - `input_schema: object` JSON Schema defining the expected input parameters for the tool. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. minLength: 1, maxLength: 128 ### Beta Managed Agents Edit Tool Config - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Edit Tool Config Params - `beta_managed_agents_edit_tool_config_params: object` Configuration override for the edit tool. - `type: optional "edit"` - `name: "edit"` Must be "edit". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Effort High - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` ### Beta Managed Agents Effort Low - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` ### Beta Managed Agents Effort Max - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` ### Beta Managed Agents Effort Medium - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` ### Beta Managed Agents Effort Xhigh - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` ### Beta Managed Agents Execution Identity - `beta_managed_agents_execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent as returned in API responses. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` ### Beta Managed Agents Execution Identity Params - `beta_managed_agents_execution_identity_params: BetaManagedAgentsAWSRoleExecutionIdentityParams or BetaManagedAgentsServiceAccountExecutionIdentityParams` Execution principal for runs of this agent: `service_account` (the default) or `aws_role`. - `beta_managed_agents_aws_role_execution_identity_params: object` An AWS IAM role principal. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN, e.g. "arn:aws:iam::123456789012:role/my-agent-runner". Maximum 2048 characters. maxLength: 2048 - `beta_managed_agents_service_account_execution_identity_params: object` The Anthropic-managed service account — the default execution principal. Carries no identifier. - `type: "service_account"` ### Beta Managed Agents Glob Tool Config - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Glob Tool Config Params - `beta_managed_agents_glob_tool_config_params: object` Configuration override for the glob tool. - `type: optional "glob"` - `name: "glob"` Must be "glob". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Grep Tool Config - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Grep Tool Config Params - `beta_managed_agents_grep_tool_config_params: object` Configuration override for the grep tool. - `type: optional "grep"` - `name: "grep"` Must be "grep". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents MCP Server URL Definition - `beta_managed_agents_mcp_server_url_definition: object` URL-based MCP server connection as returned in API responses. - `type: "url"` - `name: string` - `url: string` ### Beta Managed Agents MCP Tool Config - `beta_managed_agents_mcp_tool_config: object` Resolved configuration for a specific MCP tool. - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents MCP Tool Config Params - `beta_managed_agents_mcp_tool_config_params: object` Configuration override for a specific MCP tool. - `name: string` Name of the MCP tool to configure. 1-128 characters. minLength: 1, maxLength: 128 - `enabled: optional boolean` Whether this tool is enabled. Overrides the `default_config` setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Overrides the `default_config` setting. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents MCP Toolset - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` ### Beta Managed Agents MCP Toolset Default Config - `beta_managed_agents_mcp_toolset_default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents MCP Toolset Default Config Params - `beta_managed_agents_mcp_toolset_default_config_params: object` Default configuration for all tools from an MCP server. - `enabled: optional boolean` Whether tools are enabled by default. Defaults to true if not specified. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Default permission policy for tools from this server. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents MCP Toolset Params - `beta_managed_agents_mcp_toolset_params: object` Configuration for tools from an MCP server defined in `mcp_servers`. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. minLength: 1, maxLength: 255 - `configs: optional array of BetaManagedAgentsMCPToolConfigParams` Per-tool configuration overrides. - `name: string` Name of the MCP tool to configure. 1-128 characters. minLength: 1, maxLength: 128 - `enabled: optional boolean` Whether this tool is enabled. Overrides the `default_config` setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Overrides the `default_config` setting. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `default_config: optional object` Default configuration for all tools from this server. - `enabled: optional boolean` Whether tools are enabled by default. Defaults to true if not specified. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Default permission policy for tools from this server. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. ### Beta Managed Agents Model Config - `beta_managed_agents_model_config: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` ### Beta Managed Agents Model Config Params - `beta_managed_agents_model_config_params: object` An object that defines additional configuration control over model use - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more` How hard Claude works on each inference call. Accepts a bare level string (`"high"`) or `{"type": "high"}`. On create, omitting it resolves the per-model default; on update, omitting it leaves the stored value unchanged. - `BetaManagedAgentsEffortLevel: "low" or "medium" or "high" or 2 more` How hard Claude works on each turn. Higher levels favor reasoning depth over latency. Not all models accept every level; invalid combinations are rejected at create time. - `"low"` Low effort. Favors latency over reasoning depth. - `"medium"` Medium effort. Balances latency and reasoning depth. - `"high"` High effort. Favors reasoning depth. - `"xhigh"` Extra-high effort. Not all models accept this level. - `"max"` Maximum effort. Favors reasoning depth over latency. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it. - `speed: optional "standard" or "fast"` Inference speed mode. Defaults to `standard`. - `"standard"` - `"fast"` ### Beta Managed Agents Multiagent Advisor - `beta_managed_agents_multiagent_advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` ### Beta Managed Agents Multiagent Advisor Disabled - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` ### Beta Managed Agents Multiagent Advisor Disabled Params - `beta_managed_agents_multiagent_advisor_disabled_params: object` The agent has no advisor. - `type: "disabled"` ### Beta Managed Agents Multiagent Advisor Enabled - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. ### Beta Managed Agents Multiagent Advisor Enabled Params - `beta_managed_agents_multiagent_advisor_enabled_params: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 ### Beta Managed Agents Multiagent Advisor Params - `beta_managed_agents_multiagent_advisor_params: BetaManagedAgentsMultiagentAdvisorEnabledParams or BetaManagedAgentsMultiagentAdvisorDisabledParams` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled_params: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 - `beta_managed_agents_multiagent_advisor_disabled_params: object` The agent has no advisor. - `type: "disabled"` ### Beta Managed Agents Multiagent Coordinator - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. ### Beta Managed Agents Multiagent Coordinator Params - `beta_managed_agents_multiagent_coordinator_params: object` A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the `agents` roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsMultiagentRosterEntryParams` Agents the coordinator may spawn as session threads. 1–20 entries. Each entry is an agent ID string, a versioned `{"type":"agent","id","version"}` reference, or `{"type":"self"}` to allow recursive self-invocation. Entries must reference distinct agents (after resolving `self` and string forms); at most one `self`. Referenced agents must exist, must not be archived, and must not themselves have `multiagent` set (depth limit 1). - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - `beta_managed_agents_advisor_params: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. At most one per roster; the entry occupies the roster name `anthropic.advisor`. - `type: "advisor"` - `model: string` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 ### Beta Managed Agents Multiagent Inline Agents - `beta_managed_agents_multiagent_inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents. The agent defines an inline agent itself, in a workflow run's plan or when it spawns a session thread, and the inline agent is not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` ### Beta Managed Agents Multiagent Inline Agents Disabled - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` ### Beta Managed Agents Multiagent Inline Agents Disabled Params - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` ### Beta Managed Agents Multiagent Inline Agents Enabled - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` ### Beta Managed Agents Multiagent Inline Agents Enabled Params - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` ### Beta Managed Agents Multiagent Inline Agents Params - `beta_managed_agents_multiagent_inline_agents_params: BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether the agent can define inline agents. The agent defines an inline agent itself, in a workflow run's plan or when it spawns a session thread, and the inline agent is not saved. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` ### Beta Managed Agents Multiagent Predefined Agent Params - `beta_managed_agents_multiagent_predefined_agent_params: string or BetaManagedAgentsAgentParams or BetaManagedAgentsMultiagentSelfParams` One agent in a `predefined_agents` list. It is an agent ID string, an `agent` reference with an optional `version`, or `self` for the agent that owns this configuration. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` ### Beta Managed Agents Multiagent Self Params - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` ### Beta Managed Agents Multiagent Subagents - `beta_managed_agents_multiagent_subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` ### Beta Managed Agents Multiagent Subagents Disabled - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` ### Beta Managed Agents Multiagent Subagents Disabled Params - `beta_managed_agents_multiagent_subagents_disabled_params: object` The agent cannot spawn session threads. - `type: "disabled"` ### Beta Managed Agents Multiagent Subagents Enabled - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 ### Beta Managed Agents Multiagent Subagents Enabled Params - `beta_managed_agents_multiagent_subagents_enabled_params: object` The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in `predefined_agents`, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: "enabled"` - `inline_agents: optional BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether the agent can define inline agents when it spawns session threads. Defaults to enabled. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: optional array of BetaManagedAgentsMultiagentPredefinedAgentParams` Predefined agents that this agent can spawn as session threads. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `workflows.predefined_agents`, and an agent in one list is not added to the other. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` ### Beta Managed Agents Multiagent Subagents Params - `beta_managed_agents_multiagent_subagents_params: BetaManagedAgentsMultiagentSubagentsEnabledParams or BetaManagedAgentsMultiagentSubagentsDisabledParams` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled_params: object` The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in `predefined_agents`, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: "enabled"` - `inline_agents: optional BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether the agent can define inline agents when it spawns session threads. Defaults to enabled. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: optional array of BetaManagedAgentsMultiagentPredefinedAgentParams` Predefined agents that this agent can spawn as session threads. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `workflows.predefined_agents`, and an agent in one list is not added to the other. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - `beta_managed_agents_multiagent_subagents_disabled_params: object` The agent cannot spawn session threads. - `type: "disabled"` ### Beta Managed Agents Multiagent Workflows - `beta_managed_agents_multiagent_workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` ### Beta Managed Agents Multiagent Workflows Disabled - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` ### Beta Managed Agents Multiagent Workflows Disabled Params - `beta_managed_agents_multiagent_workflows_disabled_params: object` The agent cannot start workflow runs. - `type: "disabled"` ### Beta Managed Agents Multiagent Workflows Enabled - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 ### Beta Managed Agents Multiagent Workflows Enabled Params - `beta_managed_agents_multiagent_workflows_enabled_params: object` The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in `predefined_agents`, and inline agents, which it defines itself and which are not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: "enabled"` - `inline_agents: optional BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether a run's plan can define inline agents. Defaults to enabled. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: optional array of BetaManagedAgentsMultiagentPredefinedAgentParams` Predefined agents that a run's plan can use. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `subagents.predefined_agents`, and an agent in one list is not added to the other. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` ### Beta Managed Agents Multiagent Workflows Params - `beta_managed_agents_multiagent_workflows_params: BetaManagedAgentsMultiagentWorkflowsEnabledParams or BetaManagedAgentsMultiagentWorkflowsDisabledParams` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled_params: object` The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in `predefined_agents`, and inline agents, which it defines itself and which are not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: "enabled"` - `inline_agents: optional BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether a run's plan can define inline agents. Defaults to enabled. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: optional array of BetaManagedAgentsMultiagentPredefinedAgentParams` Predefined agents that a run's plan can use. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `subagents.predefined_agents`, and an agent in one list is not added to the other. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - `beta_managed_agents_multiagent_workflows_disabled_params: object` The agent cannot start workflow runs. - `type: "disabled"` ### Beta Managed Agents Multiagent20261001 - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` ### Beta Managed Agents Multiagent20261001 Params - `beta_managed_agents_multiagent20261001_params: object` Multiagent configuration with three members, each enabled or disabled on its own. On an update, if the agent's stored `multiagent` also has type `multiagent_20261001`, this configuration is merged into the stored one, level by level, instead of replacing it. A key that the update omits keeps its stored value. A key sent as null takes its default, on create as well, so `"workflows": null` enables workflows. An object sent with a `type` other than the stored one replaces the stored object, and the keys that it omits take their defaults. A `predefined_agents` list that is sent replaces the stored list. Every object that is sent needs its `type`, and an enabled `advisor` needs its `model`. Other validation applies to the merged result. - `type: "multiagent_20261001"` - `advisor: optional BetaManagedAgentsMultiagentAdvisorEnabledParams or BetaManagedAgentsMultiagentAdvisorDisabledParams` Whether the session's primary thread can consult an advisor model. Defaults to disabled. - `beta_managed_agents_multiagent_advisor_enabled_params: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 - `beta_managed_agents_multiagent_advisor_disabled_params: object` The agent has no advisor. - `type: "disabled"` - `subagents: optional BetaManagedAgentsMultiagentSubagentsEnabledParams or BetaManagedAgentsMultiagentSubagentsDisabledParams` Whether the agent can spawn session threads. Defaults to enabled. - `beta_managed_agents_multiagent_subagents_enabled_params: object` The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in `predefined_agents`, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: "enabled"` - `inline_agents: optional BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether the agent can define inline agents when it spawns session threads. Defaults to enabled. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: optional array of BetaManagedAgentsMultiagentPredefinedAgentParams` Predefined agents that this agent can spawn as session threads. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `workflows.predefined_agents`, and an agent in one list is not added to the other. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: "agent"` - `id: string` The `agent` ID. minLength: 1, maxLength: 128 - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - `beta_managed_agents_multiagent_subagents_disabled_params: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: optional BetaManagedAgentsMultiagentWorkflowsEnabledParams or BetaManagedAgentsMultiagentWorkflowsDisabledParams` Whether the agent can start workflow runs. Defaults to enabled. - `beta_managed_agents_multiagent_workflows_enabled_params: object` The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in `predefined_agents`, and inline agents, which it defines itself and which are not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: "enabled"` - `inline_agents: optional BetaManagedAgentsMultiagentInlineAgentsEnabledParams or BetaManagedAgentsMultiagentInlineAgentsDisabledParams` Whether a run's plan can define inline agents. Defaults to enabled. - `beta_managed_agents_multiagent_inline_agents_enabled_params: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled_params: object` The agent cannot define inline agents. - `predefined_agents: optional array of BetaManagedAgentsMultiagentPredefinedAgentParams` Predefined agents that a run's plan can use. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `subagents.predefined_agents`, and an agent in one list is not added to the other. - `union_member_0: string` - `beta_managed_agents_agent_params: object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `beta_managed_agents_multiagent_self_params: object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `beta_managed_agents_multiagent_workflows_disabled_params: object` The agent cannot start workflow runs. - `type: "disabled"` ### Beta Managed Agents Read Tool Config - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Read Tool Config Params - `beta_managed_agents_read_tool_config_params: object` Configuration override for the read tool. - `type: optional "read"` - `name: "read"` Must be "read". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Service Account Execution Identity - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` ### Beta Managed Agents Service Account Execution Identity Params - `beta_managed_agents_service_account_execution_identity_params: object` The Anthropic-managed service account — the default execution principal. Carries no identifier. - `type: "service_account"` ### Beta Managed Agents Session Thread Agent - `beta_managed_agents_session_thread_agent: object` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: "agent"` - `id: string` - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal snapshotted from the agent at session creation. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `version: number` format: int32 ### Beta Managed Agents Skill Params - `beta_managed_agents_skill_params: BetaManagedAgentsAnthropicSkillParams or BetaManagedAgentsCustomSkillParams` Skill to load in the session container. - `beta_managed_agents_anthropic_skill_params: object` An Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` Identifier of the Anthropic skill (e.g., "xlsx"). minLength: 1, maxLength: 64 - `version: optional string` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `beta_managed_agents_custom_skill_params: object` A user-created custom skill. - `type: "custom"` - `skill_id: string` Tagged ID of the custom skill (e.g., "skill_01XJ5..."). minLength: 1, maxLength: 64 - `version: optional string` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 ### Beta Managed Agents URL MCP Server Params - `beta_managed_agents_url_mcp_server_params: object` URL-based MCP server connection. - `type: "url"` - `name: string` Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. minLength: 1, maxLength: 255 - `url: string` Endpoint URL for the MCP server. maxLength: 2048 ### Beta Managed Agents User Location - `beta_managed_agents_user_location: object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 ### Beta Managed Agents Web Fetch Tool Config - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 ### Beta Managed Agents Web Fetch Tool Config Params - `beta_managed_agents_web_fetch_tool_config_params: object` Configuration override for the web_fetch tool. - `type: optional "web_fetch"` - `name: "web_fetch"` Must be "web_fetch". - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: optional array of string` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: optional number` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `url_sources: optional object` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `user_input: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceUserInput` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` ### Beta Managed Agents Web Fetch URL Source All - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` ### Beta Managed Agents Web Fetch URL Source Except - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 ### Beta Managed Agents Web Fetch URL Source None - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` ### Beta Managed Agents Web Fetch URL Source Only - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 ### Beta Managed Agents Web Fetch URL Source Shorthand - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` ### Beta Managed Agents Web Fetch URL Source Tool Filter - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 ### Beta Managed Agents Web Fetch URL Source Tool Filter Params - `beta_managed_agents_web_fetch_url_source_tool_filter_params: BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which tools' results contribute URLs that may be fetched. Accepts the string "all" or "none", or an object whose type is "all", "none", "only" or "except". Responses use the object form. - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 ### Beta Managed Agents Web Fetch URL Source Tool Reference - `beta_managed_agents_web_fetch_url_source_tool_reference: object` Names one tool in an only or except list. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 ### Beta Managed Agents Web Fetch URL Source User Input - `beta_managed_agents_web_fetch_url_source_user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` ### Beta Managed Agents Web Fetch URL Source User Input Params - `beta_managed_agents_web_fetch_url_source_user_input_params: BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceUserInput` Whether URLs in the text of user messages may be fetched. Accepts the string "all" or "none", or the object {"type": "all"} or {"type": "none"}. Responses use the object form. - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` ### Beta Managed Agents Web Fetch URL Sources - `beta_managed_agents_web_fetch_url_sources: object` Which sources contribute URLs the web_fetch tool may fetch. A key that is null was not set and allows every URL from that source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` ### Beta Managed Agents Web Fetch URL Sources Params - `beta_managed_agents_web_fetch_url_sources_params: object` Which sources contribute URLs the web_fetch tool may fetch. When web_fetch is limited to URLs the conversation has already shown the model (in a user message, a custom tool's result, or an earlier web_search or web_fetch result), each key narrows one of those sources and defaults to "all". Setting all three keys to "none" is rejected. - `client_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceToolFilter` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `beta_managed_agents_web_fetch_url_source_tool_filter: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which tools' results contribute URLs that may be fetched. - `user_input: optional BetaManagedAgentsWebFetchURLSourceShorthand or BetaManagedAgentsWebFetchURLSourceUserInput` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `beta_managed_agents_web_fetch_url_source_shorthand: "all" or "none"` String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}. - `"all"` - `"none"` - `beta_managed_agents_web_fetch_url_source_user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` ### Beta Managed Agents Web Search Tool Config - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 ### Beta Managed Agents Web Search Tool Config Params - `beta_managed_agents_web_search_tool_config_params: object` Configuration override for the web_search tool. - `type: optional "web_search"` - `name: "web_search"` Must be "web_search". - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: optional array of string` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 ### Beta Managed Agents Write Tool Config - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ### Beta Managed Agents Write Tool Config Params - `beta_managed_agents_write_tool_config_params: object` Configuration override for the write tool. - `type: optional "write"` - `name: "write"` Must be "write". - `enabled: optional boolean` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` ## Agents › Versions ### List Agent Versions `$ ant beta:agents:versions list` **GET** `/v1/agents/{agent_id}/versions` List Agent Versions #### Parameters - `--agent-id: string` (path parameter) Agent ID to list versions for. - `--limit: optional number` (query parameter) Maximum results per page. Default 20, maximum 100. format: int32 - `--page: optional string` (query parameter) Opaque pagination cursor. - `--beta: optional array of AnthropicBeta` (header parameter) This endpoint is in beta: requests must send `managed-agents-2026-04-01` in this header. - `--workspace-id: optional string` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `BetaManagedAgentsListAgentVersions: object` Paginated list of agent versions. - `data: array of BetaManagedAgentsAgent` Agent versions. - `type: "agent"` - `id: string` - `archived_at: string` When the agent was archived. Null if not archived. format: date-time - `created_at: string` A timestamp in RFC 3339 format format: date-time - `description: string` - `execution_identity: BetaManagedAgentsAWSRoleExecutionIdentity or BetaManagedAgentsServiceAccountExecutionIdentity` Execution principal for runs of this agent. Always present; `{"type": "service_account"}` when runs carry no customer-named principal. - `beta_managed_agents_aws_role_execution_identity: object` An AWS IAM role principal as returned in API responses. - `type: "aws_role"` - `role_arn: string` The IAM role's ARN. - `beta_managed_agents_service_account_execution_identity: object` The Anthropic-managed service account as returned in API responses. - `type: "service_account"` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition` - `type: "url"` - `name: string` - `url: string` - `metadata: map[string]` - `model: object` Model identifier and configuration. - `id: "claude-haiku-5-5" or "claude-sonnet-5-5" or "claude-opus-5-5" or 14 more or string` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `beta_managed_agents_effort_low: object` Low effort. Favors latency over reasoning depth. - `type: "low"` - `beta_managed_agents_effort_medium: object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - `beta_managed_agents_effort_high: object` High effort. Favors reasoning depth. - `type: "high"` - `beta_managed_agents_effort_xhigh: object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - `beta_managed_agents_effort_max: object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: optional "standard" or "fast"` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: BetaManagedAgentsMultiagentCoordinator or BetaManagedAgentsMultiagent20261001` Multiagent orchestration configuration. Null when the agent is single-threaded. - `beta_managed_agents_multiagent_coordinator: object` Resolved coordinator topology with a concrete agent roster. - `type: "coordinator"` - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `beta_managed_agents_agent_reference: object` A resolved agent reference with a concrete version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_advisor: object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: "advisor"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent20261001: object` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: "multiagent_20261001"` - `advisor: BetaManagedAgentsMultiagentAdvisorEnabled or BetaManagedAgentsMultiagentAdvisorDisabled` Whether the session's primary thread can consult an advisor model. - `beta_managed_agents_multiagent_advisor_enabled: object` The session's primary thread can consult `model` mid-turn. - `type: "enabled"` - `model: string` The advisor model id. - `beta_managed_agents_multiagent_advisor_disabled: object` The agent has no advisor. - `type: "disabled"` - `subagents: BetaManagedAgentsMultiagentSubagentsEnabled or BetaManagedAgentsMultiagentSubagentsDisabled` Whether the agent can spawn session threads. - `beta_managed_agents_multiagent_subagents_enabled: object` The agent can spawn session threads. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `type: "enabled"` - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `type: "disabled"` - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_subagents_disabled: object` The agent cannot spawn session threads. - `type: "disabled"` - `workflows: BetaManagedAgentsMultiagentWorkflowsEnabled or BetaManagedAgentsMultiagentWorkflowsDisabled` Whether the agent can start workflow runs. - `beta_managed_agents_multiagent_workflows_enabled: object` The agent can start workflow runs. - `type: "enabled"` - `inline_agents: BetaManagedAgentsMultiagentInlineAgentsEnabled or BetaManagedAgentsMultiagentInlineAgentsDisabled` Whether a run's plan can define inline agents, which are not saved. - `beta_managed_agents_multiagent_inline_agents_enabled: object` The agent can define inline agents. - `beta_managed_agents_multiagent_inline_agents_disabled: object` The agent cannot define inline agents. - `predefined_agents: array of BetaManagedAgentsAgentReference` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: "agent"` - `id: string` - `version: number` format: int32 - `beta_managed_agents_multiagent_workflows_disabled: object` The agent cannot start workflow runs. - `type: "disabled"` - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - `beta_managed_agents_anthropic_skill: object` A resolved Anthropic-managed skill. - `type: "anthropic"` - `skill_id: string` - `version: string` - `beta_managed_agents_custom_skill: object` A resolved user-created custom skill. - `type: "custom"` - `skill_id: string` - `version: string` - `system: string` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - `beta_managed_agents_agent_toolset20260401: object` - `type: "agent_toolset_20260401"` - `configs: array of BetaManagedAgentsAgentToolConfig` - `beta_managed_agents_bash_tool_config: object` Configuration for the bash tool. - `type: "bash"` - `enabled: boolean` - `name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `type: "always_ask"` - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: "auto"` - `beta_managed_agents_edit_tool_config: object` Configuration for the edit tool. - `type: "edit"` - `enabled: boolean` - `name: "edit"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_read_tool_config: object` Configuration for the read tool. - `type: "read"` - `enabled: boolean` - `name: "read"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_write_tool_config: object` Configuration for the write tool. - `type: "write"` - `enabled: boolean` - `name: "write"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_glob_tool_config: object` Configuration for the glob tool. - `type: "glob"` - `enabled: boolean` - `name: "glob"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_grep_tool_config: object` Configuration for the grep tool. - `type: "grep"` - `enabled: boolean` - `name: "grep"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_web_fetch_tool_config: object` Configuration for the web_fetch tool. - `type: "web_fetch"` - `enabled: boolean` - `name: "web_fetch"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: object` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `type: "only"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: "except"` - `tools: array of BetaManagedAgentsWebFetchURLSourceToolReference` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: "tool_reference"` Must be "tool_reference". - `name: string` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone or BetaManagedAgentsWebFetchURLSourceOnly or BetaManagedAgentsWebFetchURLSourceExcept` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_only: object` Only the named tools' results contribute URLs that may be fetched. - `beta_managed_agents_web_fetch_url_source_except: object` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `user_input: BetaManagedAgentsWebFetchURLSourceAll or BetaManagedAgentsWebFetchURLSourceNone` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `beta_managed_agents_web_fetch_url_source_all: object` Every URL from this source may be fetched. This is the default. - `type: "all"` - `beta_managed_agents_web_fetch_url_source_none: object` This source contributes no URLs that may be fetched. - `type: "none"` - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number` format: int32 - `beta_managed_agents_web_search_tool_config: object` Configuration for the web_search tool. - `type: "web_search"` - `enabled: boolean` - `name: "web_search"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `user_location: optional object` Approximate user location for search result localization. - `type: "approximate"` Location precision. Only "approximate" is supported. - `city: optional string` City name. minLength: 1, maxLength: 255 - `country: optional string` Two-letter ISO 3166-1 country code, uppercase. - `region: optional string` Region or state name. minLength: 1, maxLength: 255 - `timezone: optional string` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: object` Resolved default configuration for agent tools. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `beta_managed_agents_mcp_toolset: object` - `type: "mcp_toolset"` - `configs: array of BetaManagedAgentsMCPToolConfig` - `enabled: boolean` - `name: string` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: object` Resolved default configuration for all tools from an MCP server. - `enabled: boolean` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution. - `beta_managed_agents_always_allow_policy: object` Tool calls are automatically approved without user confirmation. - `beta_managed_agents_always_ask_policy: object` Tool calls require user confirmation before execution. - `beta_managed_agents_auto_policy: object` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: string` - `beta_managed_agents_custom_tool: object` A custom tool as returned in API responses. - `type: "custom"` - `description: string` - `input_schema: object` JSON Schema for custom tool input parameters. - `type: "object"` - `properties: optional map[unknown]` - `required: optional array of string` - `name: string` - `updated_at: string` A timestamp in RFC 3339 format format: date-time - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 - `next_page: optional string` Opaque cursor for the next page. Null when no more results. #### Example ```bash ant beta:agents:versions list \ --api-key my-anthropic-api-key \ --agent-id agent_011CZkYpogX7uDKUyvBTophP ``` ##### Response (200) ```json { "data": [ { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "execution_identity": { "type": "service_account" }, "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ], "next_page": "next_page" } ```