Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
This page collects reference material for Claude Managed Agents. For task-oriented guides, follow the links in each section. For the operations on the session resource, see Session operations.
Managed Agents API requests require the managed-agents-2026-04-01 beta header, except memory store endpoints, which use agent-memory-2026-07-22 instead. The SDK sets the correct beta header automatically. See Beta headers.
Persisted event type strings follow a {domain}.{action} naming convention; the stream-only event deltas (see the Event deltas tab) are the exception. See Session event stream for sending, streaming, and listing events.
| Type | Description |
|---|---|
user.message | A user message with text content. |
user.interrupt | Stop the agent mid-execution. |
user.custom_tool_result | Response to a custom tool call from the agent. |
user.tool_confirmation | Approve or deny an agent or MCP tool call when a permission policy requires confirmation. |
user.define_outcome | Define an outcome for the agent to work toward. |
user.tool_result | For sessions with self_hosted environments only, your integration is responsible for providing agent_toolset results. The SDK helpers and CLI do this automatically. |
These are the ant beta:worker CLI flags for the pre-built worker that drives a self_hosted environment. See Self-hosted sandboxes for setting up the environment, running a worker, and the SDK helper options.
| Flag | Description |
|---|---|
--environment-id | The environment to poll for work. Also reads from ANTHROPIC_ENVIRONMENT_ID. |
--environment-key | Authenticates the worker with this environment. Also reads from ANTHROPIC_ENVIRONMENT_KEY. |
--workdir | Directory where skills are downloaded and tools read and write files. Defaults to . (the current directory); the system default working directory is /workspace. |
--on-work | Script to call for each claimed work item instead of running tools in-process. Receives session details as environment variables. |
--unrestricted-paths | Allow tool calls to access paths outside --workdir. |
--max-idle | How long to wait after the session goes idle with an end_turn stop reason before shutting down. Defaults to 60s. |
--log-format | Log output format. Use json for structured log ingestion. Defaults to text. |
Claude Managed Agents connects to remote MCP servers that expose an HTTP endpoint, or to private MCP servers through MCP tunnels. The server must support the MCP protocol's streamable HTTP transport. See MCP connector for declaring servers on an agent.
For more information on MCP and building MCP servers, see the MCP documentation.
Managed Agents endpoints are rate-limited per organization:
| Operation | Limit |
|---|---|
| Create endpoints (such as agents, sessions, and environments) | 300 requests per minute |
| Read endpoints (such as retrieve, list, and stream) | 1,200 requests per minute |
Organization-level spend limits and usage-tier rate limits also apply.
For partners integrating Claude Managed Agents, use of Claude branding is optional. When referencing Claude in your product:
Allowed:
Not permitted:
Your product should maintain its own branding and not appear to be Claude Code, Claude Cowork, or any other Anthropic product. For questions about branding compliance, contact the Anthropic sales team.
Was this page helpful?