whoamiLABSCO SUMMARY
Read-first, with the three dangerous tools saying so in their own descriptions.
Prefixing the mutating tools' descriptions with a warning is a small thing that changes model behaviour — it makes cancelling a run a deliberate act rather than a plausible next step. The pairing that earns its keep is a failed run and its logs in two calls, then a replay in a third, without switching to the dashboard to do it.
What it is
A wrapper over the Hatchet API. Seven tools read state — definitions, runs, logs, workers, queue health — and three change it, each labelled as mutating so nobody calls one by accident.
What you get
- list_workflows and list_runs, the latter with a lookback window and filters
- get_run — one run in full: status, its tasks, and the errors
- get_run_logs for a task's log lines by its external id
- list_workers and get_queue_metrics for whether anything is actually picking work up
- whoami, which confirms the token works and shows which tenant and server it resolved to
- trigger_workflow to start a run by name with a JSON payload
- cancel_runs and replay_runs across one or more ids at a time
Requirements
HATCHET_CLIENT_TOKEN, a JWT from the dashboard that encodes both the server URL and the tenant — normally the only setting needed. HATCHET_API_BASE points it at a self-hosted instance, and HATCHET_TENANT_ID overrides what the token decoded. Runs from npx. The token grants full tenant access, so treat it accordingly.
Setup effort
One command plus a key — npx -y hatchet-mcp, then supply credentials
USE CASES
01
Finding out why a run failed
Open the run for its tasks and errors, then pull the log lines for the task that broke.
02
Checking whether work is being picked up at all
Look at the workers and the queue metrics before assuming the workflow is at fault.
03
Re-running something after the fix
Replay the failed runs by id rather than triggering fresh ones.
04
Stopping a run that should not be going
Cancel it, or several of them, by external id.
05
Kicking off a workflow with specific input
Trigger it by name with the JSON payload it expects.
06
Confirming you are pointed at the right place
Check which tenant and server the token resolved to before acting on anything.
10 tools
Listed in project docs. Your client may show a different list.
list_workflowslist_runsget_runget_run_logslist_workersget_queue_metricstrigger_workflowcancel_runsreplay_runsBEFORE YOU INSTALL
What to know first
Tools you get
10 tools named in the project's documentation.
Requires
- npx on PATH
- HATCHET_CLIENT_TOKEN in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y hatchet-mcpMCP Clients
Claude Code, Claude Desktop
JSON
{
"mcpServers": {
"hatchet": {
"command": "npx",
"args": [
"-y",
"hatchet-mcp"
],
"env": {
"HATCHET_CLIENT_TOKEN": "<YOUR_HATCHET_CLIENT_TOKEN>"
}
}
}
}
