> This page is for Agent Handler.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.merge.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.merge.dev/_mcp/server.

# Warp (warp.dev)

**Authentication:** API key. See [Magic Link](/merge-agent-handler/features/magic-link) for the runtime auth flow.

## Sample use cases

* Start a cloud agent run that fixes the failing test in `api/handlers_test.go`
* List the scheduled agents in the team and when each runs next
* Fetch the artifacts produced by the last agent run

## Available Tools

#### cancel_run

Cancel an in-flight agent run by id. Only runs whose type is cancellable and that are not already in a terminal state...

#### create_agent

Create a new agent identity. Requires a name. Use list_environments for environment_id, list_models for base_model, l...

#### create_run

Start a new agent run from a prompt (or a skill spec). Returns the new run_id and initial state. Use list_agent_skill...

#### create_scheduled_agent

Create a scheduled agent that triggers runs on a cron schedule. Requires name and cron_schedule. Use list_agents for...

#### delete_agent

Delete an agent identity permanently by uid. The default agent cannot be deleted. Use list_agents to find uids.

#### delete_scheduled_agent

Delete a scheduled agent permanently by id. Use list_scheduled_agents to find ids.

#### download_artifact

Get a signed URL to download an artifact's file contents by uid. The API responds with a 302 redirect to a time-limit...

#### get_agent

Get full detail for a single agent identity by uid. Use list_agents to find uids.

#### get_artifact

Get metadata for a run artifact by uid (type, filename, mime type, size). Artifact uids come from a run's artifacts f...

#### get_run

Get full detail for a single agent run by id, including state, prompt, creator, timing, and artifacts. Use list_runs...

#### get_run_transcript

Get a signed URL to download the full transcript of a run. Use list_runs to find run ids. The API responds with a 302...

#### get_scheduled_agent

Get full detail for a single scheduled agent by id. Use list_scheduled_agents to find ids.

#### list_agent_skills

List discoverable agent skills from the /agent catalog and their variants (skill specs). Use the returned variant ids...

#### list_agents

List agent identities for the team. Agent identities are the execution principals a run or schedule can run as. Use g...

#### list_connected_self_hosted_workers

List self-hosted worker hosts currently connected to the team, with connection counts and heartbeat timestamps. Use t...

#### list_environments

List the cloud environments available for agent runs. Use the returned environment uids for environment_id on create\_...

#### list_models

List the LLM models available for agent runs and the team's default model id. Use the returned model ids for base_mod...

#### list_runs

List agent runs with optional server-side filters (state, name, q, creator, model_id, source, execution_location, sch...

#### list_scheduled_agents

List all scheduled agents for the team, including their cron schedule and enabled state. Use get_scheduled_agent for...

#### pause_scheduled_agent

Pause a scheduled agent by id so it stops triggering runs. Use resume_scheduled_agent to re-enable it. Use list_sched...

#### resume_scheduled_agent

Resume a paused scheduled agent by id so it triggers runs again. Use pause_scheduled_agent to disable it. Use list_sc...

#### update_agent

Update an agent identity by uid. Only the fields you pass are changed (partial update). Use list_agents to find uids...

#### update_scheduled_agent

Update a scheduled agent by id. This is a full replace (PUT): name, cron_schedule, and enabled are all required. Use...