Managed AgentsReference

Reference

Event types, self-hosted worker CLI flags, supported MCP server types, rate limits, and branding guidelines for Claw Managed Agents.

This page collects reference material for Claw 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.

Event types

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, image, or document 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.

Self-hosted worker

These are the eno 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 `ENOPHIC_ENVIRONMENT_ID`.
`--environment-key`	Authenticates the worker with this environment. Also reads from `ENOPHIC_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 the file tools to read and write paths outside `--workdir`. The workdir check is a guardrail for the file tools only, not a sandbox; it does not constrain bash.
`--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`.

Supported MCP server types

Claw Managed Agents connects to remote MCP servers that expose an HTTP endpoint, or to private MCP servers through MCP tunnels. The server should support the MCP protocol's streamable HTTP transport; servers that only support the deprecated SSE transport still work through an automatic fallback. See MCP connector for declaring servers on an agent.

For more information on MCP and building MCP servers, see the MCP documentation.

Rate limits

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.

Branding guidelines

For partners integrating Claw Managed Agents, use of Claw branding is optional. When referencing Claw in your product:

Allowed:

"Claw Agent" (preferred for dropdown menus)
"Claw" (when within a menu already labeled "Agents")
"{YourAgentName} Powered by Claw" (if you have an existing agent name)

Not permitted:

"Claw Code" or "Claw Code Agent"
"Claw Cowork" or "Claw Cowork Agent"
Claw Code-branded ASCII art or visual elements that mimic Claw Code

Your product should maintain its own branding and not appear to be Claw Code, Claw Cowork, or any other Enophic product. For questions about branding compliance, contact the Enophic sales team.

¿Te ha resultado útil esta página?

Managed AgentsReference

Reference

Event types, self-hosted worker CLI flags, supported MCP server types, rate limits, and branding guidelines for Claw Managed Agents.

This page collects reference material for Claw Managed Agents. For task-oriented guides, follow the links in each section. For the operations on the session resource, see Session operations.

Event types

Type	Description
`user.message`	A user message with text, image, or document 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.

Self-hosted worker

Flag	Description
`--environment-id`	The environment to poll for work. Also reads from `ENOPHIC_ENVIRONMENT_ID`.
`--environment-key`	Authenticates the worker with this environment. Also reads from `ENOPHIC_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 the file tools to read and write paths outside `--workdir`. The workdir check is a guardrail for the file tools only, not a sandbox; it does not constrain bash.
`--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`.

Supported MCP server types

For more information on MCP and building MCP servers, see the MCP documentation.

Rate limits

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.

Branding guidelines

For partners integrating Claw Managed Agents, use of Claw branding is optional. When referencing Claw in your product:

Allowed:

"Claw Agent" (preferred for dropdown menus)
"Claw" (when within a menu already labeled "Agents")
"{YourAgentName} Powered by Claw" (if you have an existing agent name)

Not permitted:

"Claw Code" or "Claw Code Agent"
"Claw Cowork" or "Claw Cowork Agent"
Claw Code-branded ASCII art or visual elements that mimic Claw Code

Your product should maintain its own branding and not appear to be Claw Code, Claw Cowork, or any other Enophic product. For questions about branding compliance, contact the Enophic sales team.

¿Te ha resultado útil esta página?

Event types

Self-hosted worker

Supported MCP server types

Rate limits

Branding guidelines

Event types

Self-hosted worker

Supported MCP server types

Rate limits

Branding guidelines

Event types

Self-hosted worker

Supported MCP server types

Rate limits

Branding guidelines

Event types

Self-hosted worker

Supported MCP server types

Rate limits

Branding guidelines