Observe and operate Hatchet workflows from an AI agent β runs, logs, trigger, cancel, replay.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Hatchet Mcp.
whoamiShow the resolved Hatchet tenant + server URL and confirm the token works.
list_workflowsList workflow definitions for the tenant.
list_runsList workflow runs (with an optional lookback window and filters).
get_runGet the full detail of one workflow run β status, tasks, errors.
get_run_logsGet log lines for a task by its external id.
list_workersList workers and their status.
An MCP server that lets AI agents observe and operate Hatchet workflows β status, runs, logs, workers, and metrics, plus trigger / cancel / replay.
Why: Hatchet has a great API but no MCP. This wraps it so agents (Claude Code / Desktop, etc.) can see and act on workflow state.
Add this to your Claude Code / Claude Desktop MCP config:
Get the token from the Hatchet dashboard β API tokens. The token is a JWT that encodes the server URL and tenant, so it's the only required setting.
| Variable | Required | Description |
|---|---|---|
HATCHET_CLIENT_TOKEN | Yes | Hatchet API token (JWT). Encodes the server URL + tenant, so it's normally all you need. |
HATCHET_API_BASE | No | Override the API base URL. Self-hosters can point this at any Hatchet instance. |
HATCHET_TENANT_ID | No | Override the tenant id decoded from the token. |
Self-hosting? Set HATCHET_API_BASE to your own Hatchet instance and it works anywhere.
| Tool | Description |
|---|---|
whoami | Show the resolved Hatchet tenant + server URL and confirm the token works. |
list_workflows | List workflow definitions for the tenant. |
list_runs | List workflow runs (with an optional lookback window and filters). |
get_run | Get the full detail of one workflow run β status, tasks, errors. |
get_run_logs | Get log lines for a task by its external id. |
list_workers | List workers and their status. |
get_queue_metrics | Get task/queue metrics for the tenant (queue health). |
| Tool | Description |
|---|---|
trigger_workflow | Trigger a new workflow run by name with a JSON input payload. |
cancel_runs | Cancel one or more runs/tasks by external id. |
replay_runs | Replay/retry one or more runs/tasks by external id. |
The read tools (whoami, list_workflows, list_runs, get_run, get_run_logs, list_workers, get_queue_metrics) are non-destructive.
trigger_workflow, cancel_runs, and replay_runs mutate live state β their descriptions are prefixed MUTATES LIVE STATE so agents and users know they affect real runs.
The token grants full tenant access β treat it as a secret. Never commit it to source control.
TypeScript / ESM, tested with vitest.
v0.1.0 β all tools verified against Hatchet Cloud; works with self-hosted instances via HATCHET_API_BASE. trigger_workflow uses the stable /workflow-runs/trigger endpoint.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/hatchet-mcp)<a href="https://allmcps.com/mcp/hatchet-mcp"><img src="https://allmcps.com/api/badge/hatchet-mcp?style=directory" alt="Hatchet Mcp on AllMCPs" /></a>