How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Anthropic Agents?beta=true API

The Agents?beta=true API from Anthropic — 1 operation(s) for agents?beta=true.

Anthropic Agents?beta=true API is one of 43 APIs that Anthropic publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Agents?beta=true. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.

This API exposes 2 operations across 1 path, and defines 86 schemas. It is described by OpenAPI 3.2.0.

Requests are made against a single base URL, https://api.anthropic.com.

2 operations 1 paths 86 schemas 1 GET1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
Base URL
https://api.anthropic.com/v1
Resource Areas
1

Paths & Operations 2

Across 1 path, the API surfaces 2 operations — 1 GET, 1 POST. Each is listed below with its method, path, parameters, and response codes.

Agents?beta=true 2
POST
/v1/agents?beta=true
Create Agent
BetaCreateAgent 2 params body → 200400401403404408409412
GET
/v1/agents?beta=true
List Agents
BetaListAgents 8 params → 200400401403404408409412

Schemas 86

The contract defines 86 schemas that model the data the API accepts and returns. The most detailed are BetaManagedAgentsAgent (15 properties), BetaManagedAgentsCreateAgentParams (9 properties), BetaManagedAgentsWebFetchToolConfig (7 properties), BetaManagedAgentsWebFetchToolConfigParams (7 properties). Each schema is shown below with its type and property counts.

BetaManagedAgentsMCPToolsetParams
object
Configuration for tools from an MCP server defined in mcpservers.
4 properties 2 required
BetaManagedAgentsMultiagentRosterEntryParams
An entry in a multiagent roster: an agent ID string, a versioned agent reference, or self.
BetaManagedAgentsAdvisorParams
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.…
2 properties 2 required
BetaManagedAgentsMCPToolConfig
object
Resolved configuration for a specific MCP tool.
3 properties 3 required
BetaManagedAgentsAgentReference
object
A resolved agent reference with a concrete version.
3 properties 3 required
BetaManagedAgentsMCPToolsetDefaultConfig
object
Resolved default configuration for all tools from an MCP server.
2 properties 2 required
BetaManagedAgentsEffortHigh
object
High effort. Favors reasoning depth.
1 property 1 required
BetaManagedAgentsCustomToolParams
object
A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an agent.customtooluse event is emitted and the session…
4 properties 4 required
BetaManagedAgentsMultiagentCoordinatorParams
object
A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the agents roster.
2 properties 2 required
BetaManagedAgentsAgentToolset20260401Params
object
Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent.
3 properties 1 required
BetaManagedAgentsWriteToolConfig
object
Configuration for the write tool.
4 properties 4 required
BetaManagedAgentsModelConfig
object
Model identifier and configuration.
4 properties 1 required
BetaManagedAgentsMultiagentSelfParams
object
Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference.
1 property 1 required
BetaManagedAgentsMultiagentCoordinator
object
Resolved coordinator topology with a concrete agent roster.
2 properties 2 required
BetaManagedAgentsPermissionPolicy
object
Permission policy for tool execution.
BetaManagedAgentsCustomSkillParams
object
A user-created custom skill.
3 properties 2 required
BetaManagedAgentsModelConfigParams
object
An object that defines additional configuration control over model use
4 properties 1 required
BetaManagedAgentsAgentToolConfigUnion
object
Configuration for a specific agent tool.
BetaManagedAgentsCustomSkill
object
A resolved user-created custom skill.
3 properties 3 required
BetaManagedAgentsMultiagentParams
Multiagent orchestration configuration. Currently supports the coordinator topology.
BetaManagedAgentsMCPToolConfigParams
object
Configuration override for a specific MCP tool.
3 properties 1 required
BetaManagedAgentsGlobToolConfig
object
Configuration for the glob tool.
4 properties 4 required
BetaManagedAgentsReadToolConfigParams
object
Configuration override for the read tool.
4 properties 1 required
BetaGatewayTimeoutError
object
2 properties 2 required
BetaManagedAgentsMultiagentRosterEntry
A resolved multiagent roster entry.
BetaManagedAgentsAgentToolsetDefaultConfigParams
object
Default configuration for all tools in a toolset.
2 properties
BetaManagedAgentsGrepToolConfig
object
Configuration for the grep tool.
4 properties 4 required
BetaManagedAgentsModel
The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
BetaManagedAgentsWebFetchToolConfigParams
object
Configuration override for the webfetch tool.
7 properties 1 required
BetaManagedAgentsAnthropicSkill
object
A resolved Anthropic-managed skill.
3 properties 3 required
BetaManagedAgentsCustomToolInputSchema
object
JSON Schema for custom tool input parameters.
3 properties 1 required
BetaManagedAgentsAgentToolset20260401
object
3 properties 3 required
BetaManagedAgentsCreateAgentParams
object
Request parameters for creating an agent.
9 properties 2 required
BetaManagedAgentsAnthropicSkillParams
object
An Anthropic-managed skill.
3 properties 2 required
BetaManagedAgentsEffortXhigh
object
Extra-high effort. Not all models accept this level.
1 property 1 required
BetaManagedAgentsGrepToolConfigParams
object
Configuration override for the grep tool.
4 properties 1 required
BetaManagedAgentsAgentToolParams
object
Union type for tool configurations in the tools array.
BetaManagedAgentsMCPServer
object
Union type for MCP server connection definitions returned in API responses.
BetaManagedAgentsAgentToolConfigUnionParams
object
Configuration override for a specific tool within a toolset.
BetaManagedAgentsAgentParams
object
Specification for an Agent. Provide a specific version or use the short-form agent="agentid" for the most recent version
3 properties 2 required
BetaManagedAgentsBashToolConfigParams
object
Configuration override for the bash tool.
4 properties 1 required
BetaManagedAgentsMCPServerParams
object
Union type for MCP server connection definitions.
BetaAPIError
object
2 properties 2 required
BetaManagedAgentsWebSearchToolConfigParams
object
Configuration override for the websearch tool.
7 properties 1 required
BetaManagedAgentsEffortLevel
string
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 c…
BetaManagedAgentsWriteToolConfigParams
object
Configuration override for the write tool.
4 properties 1 required
BetaRateLimitError
object
2 properties 2 required
BetaManagedAgentsMCPServerURLDefinition
object
URL-based MCP server connection as returned in API responses.
3 properties 3 required
BetaManagedAgentsUserLocation
object
Approximate user location for search result localization.
5 properties 1 required
BetaManagedAgentsModelParams
BetaManagedAgentsReadToolConfig
object
Configuration for the read tool.
4 properties 4 required
BetaManagedAgentsSpeed
string
Inference speed mode. fast provides significantly faster output token generation at premium pricing. Not all models support fast; invalid combinations are reje…
BetaManagedAgentsMCPToolset
object
4 properties 4 required
BetaInvalidRequestError
object
2 properties 2 required
BetaManagedAgentsWebSearchToolConfig
object
Configuration for the websearch tool.
7 properties 4 required
BetaManagedAgentsAgentTool
object
Union type for tool configurations returned in API responses.
BetaManagedAgentsEffortMedium
object
Medium effort. Balances latency and reasoning depth.
1 property 1 required
BetaManagedAgentsEffortLow
object
Low effort. Favors latency over reasoning depth.
1 property 1 required
BetaManagedAgentsGlobToolConfigParams
object
Configuration override for the glob tool.
4 properties 1 required
BetaManagedAgentsEffortParams
BetaManagedAgentsURLMCPServerParams
object
URL-based MCP server connection.
3 properties 3 required
BetaManagedAgentsListAgents
object
Paginated list of agents.
2 properties 1 required
BetaManagedAgentsAgent
object
A Managed Agents agent.
15 properties 15 required
BetaTimestamp
string
A timestamp in RFC 3339 format
BetaOverloadedError
object
2 properties 2 required
BetaBillingError
object
2 properties 2 required
BetaManagedAgentsEditToolConfig
object
Configuration for the edit tool.
4 properties 4 required
BetaManagedAgentsEffortMax
object
Maximum effort. Favors reasoning depth over latency.
1 property 1 required
BetaManagedAgentsEditToolConfigParams
object
Configuration override for the edit tool.
4 properties 1 required
BetaManagedAgentsAlwaysAskPolicy
object
Tool calls require user confirmation before execution.
1 property 1 required
BetaAuthenticationError
object
2 properties 2 required
BetaNotFoundError
object
2 properties 2 required
BetaManagedAgentsAdvisor
object
Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
2 properties 2 required
BetaManagedAgentsSkillParams
Skill to load in the session container.
BetaManagedAgentsEffort
object
How hard Claude works on each turn. Sets outputconfig.effort on every Messages call the session makes.
BetaPermissionError
object
2 properties 2 required
BetaManagedAgentsAgentToolsetDefaultConfig
object
Resolved default configuration for agent tools.
2 properties 2 required
BetaManagedAgentsBashToolConfig
object
Configuration for the bash tool.
4 properties 4 required
BetaManagedAgentsSkill
Resolved skill as returned in API responses.
BetaManagedAgentsAlwaysAllowPolicy
object
Tool calls are automatically approved without user confirmation.
1 property 1 required
BetaManagedAgentsMultiagent
Resolved multiagent orchestration configuration as returned in API responses.
BetaManagedAgentsMCPToolsetDefaultConfigParams
object
Default configuration for all tools from an MCP server.
2 properties
BetaManagedAgentsCustomTool
object
A custom tool as returned in API responses.
4 properties 4 required
BetaErrorResponse
object
3 properties 3 required
BetaManagedAgentsWebFetchToolConfig
object
Configuration for the webfetch tool.
7 properties 4 required
AnthropicBeta

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

anthropic-agents-beta-true-api-openapi.yml Raw ↑

Other APIs Anthropic publishes across the network.

Anthropic Messages API
Anthropic Models API
Anthropic Files API
Anthropic Skills API
Anthropic Agents API
Anthropic Api Keys API
Anthropic Cost API
Anthropic Environments API
Anthropic Events API
Anthropic Organization API
Anthropic Organization Invites API
Anthropic Organization Members API
Where this information came from

This is an independent, third-party profile of Anthropic Agents?beta=true API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.