An MCP server that lets AI agents observe and operate Hatchet workflows — 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:
{
"mcpServers": {
"hatchet": {
"command": "npx",
"args": ["-y", "hatchet-mcp"],
"env": { "HATCHET_CLIENT_TOKEN": "<your-hatchet-api-token>" }
}
}
}Get the token from the Hatchet dashboard → API tokens. The token is a JWT that encodes the server URL and tenant, so it's the only required setting.
Related MCP server: hatchet-mcp
Variable | Required | Description |
| Yes | Hatchet API token (JWT). Encodes the server URL + tenant, so it's normally all you need. |
| No | Override the API base URL. Self-hosters can point this at any Hatchet instance. |
| 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 |
| Show the resolved Hatchet tenant + server URL and confirm the token works. |
| List workflow definitions for the tenant. |
| List workflow runs (with an optional lookback window and filters). |
| Get the full detail of one workflow run — status, tasks, errors. |
| Get log lines for a task by its external id. |
| List workers and their status. |
| Get task/queue metrics for the tenant (queue health). |
Tool | Description |
| Trigger a new workflow run by name with a JSON input payload. |
| Cancel one or more runs/tasks by external id. |
| 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 — their descriptions are prefixed MUTATES LIVE STATE so agents and users know they affect real runs.
The token grants full tenant access — treat it as a secret. Never commit it to source control.
pnpm install
pnpm test # vitest
pnpm build # tsup -> dist/index.jsTypeScript / ESM, tested with vitest.
v0.1.0 — all tools verified against Hatchet Cloud; works with self-hosted instances via HATCHET_API_BASE. trigger_workflow uses the stable /workflow-runs/trigger endpoint.
This server cannot be deployed
Give your AI agents the tools to build, manage, and run automation workflows.
AI agent observability for production traces, natural-language insights, and improvement loops.
Data + AI observability — monitor and troubleshoot production-grade agents and the context they use.
Production observability for AI agents: search runs, read evaluations, acknowledge incidents.
