MCP Hub
Back to servers

Hatchet MCP Server

Enables monitoring and debugging of Hatchet workflows and jobs through MCP clients like Claude Code. Users can list workflows, track run statuses, query queue metrics, and retrieve job results using natural language commands.

glama
Stars
1
Updated
Feb 10, 2026
Validated
Apr 27, 2026

Hatchet MCP Server

MCP server for debugging and monitoring Hatchet jobs from Claude Code or other MCP clients.

Installation

git clone https://github.com/GJakobi/hatchet-mcp.git
cd hatchet-mcp
uv sync

Configuration

Add to your .mcp.json (Claude Code) or MCP client config:

{
  "mcpServers": {
    "hatchet": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "--directory", "/path/to/hatchet-mcp", "python", "-m", "hatchet_mcp.server"],
      "env": {
        "HATCHET_CLIENT_TOKEN": "your-hatchet-token"
      }
    }
  }
}

Available Tools

ToolDescription
list_workflowsList all registered Hatchet workflows
list_runsList workflow runs with filters (workflow_name, status, since_hours, limit)
get_run_statusGet status of a specific run by ID
get_run_resultGet the output/result of a completed run
get_queue_metricsGet job counts by status (queued, running, completed, failed)
search_runsSearch runs by metadata (e.g., audit_id, patient_id)

Example Usage

Once configured in Claude Code:

> List all Hatchet workflows
Uses: mcp__hatchet__list_workflows

> Show me runs that failed in the last 24 hours
Uses: mcp__hatchet__list_runs with status="failed"

> Find all runs for audit_id abc123
Uses: mcp__hatchet__search_runs with metadata_key="audit_id", metadata_value="abc123"

> What's the current queue depth?
Uses: mcp__hatchet__get_queue_metrics

Status Values

  • queued - Waiting to be processed
  • running - Currently executing
  • completed - Finished successfully
  • failed - Finished with error
  • cancelled - Manually cancelled

License

MIT

Reviews

No reviews yet

Sign in to write a review