Claude MarketplacesSubmit

Hatchet Mcp

elliotpadfield/hatchet-mcp

Wraps the Hatchet workflow orchestration API so Claude can see and control your distributed task execution. You get read access to workflow definitions, run history, logs, worker status, and queue metrics, plus three write operations: trigger new runs with JSON payloads, cancel in-flight tasks, and replay failed ones. The token is a JWT that encodes your tenant and server URL, so self-hosters can point it at any Hatchet instance via HATCHET_API_BASE. Reach for this when you want an agent to debug stuck workflows, correlate logs across retries, or trigger runs based on patterns it spots in your system state.

GitHub stars: 1
tools: 10
auth: Secret needed
transport: STDIO
env vars: 3
last updated: May 30, 2026

Tools

10 tools

Public tool metadata for what this MCP can expose to an agent.

whoamiShow the resolved Hatchet tenant + server URL and confirm the token works.

Show the resolved Hatchet tenant + server URL and confirm the token works.

No parameter schema in public metadata yet.

list_workflowsList workflow definitions for the tenant.

List workflow definitions for the tenant.

No parameter schema in public metadata yet.

list_runsList workflow runs (with an optional lookback window and filters).

List workflow runs (with an optional lookback window and filters).

No parameter schema in public metadata yet.

get_runGet the full detail of one workflow run — status, tasks, errors.

Get the full detail of one workflow run — status, tasks, errors.

No parameter schema in public metadata yet.

get_run_logsGet log lines for a task by its external id.

Get log lines for a task by its external id.

No parameter schema in public metadata yet.

list_workersList workers and their status.

List workers and their status.

No parameter schema in public metadata yet.

get_queue_metricsGet task/queue metrics for the tenant (queue health).

Get task/queue metrics for the tenant (queue health).

No parameter schema in public metadata yet.

trigger_workflowMUTATES LIVE STATE. Trigger a new workflow run by name with a JSON input payload.

MUTATES LIVE STATE. Trigger a new workflow run by name with a JSON input payload.

No parameter schema in public metadata yet.

cancel_runsMUTATES LIVE STATE. Cancel one or more runs/tasks by external id.

MUTATES LIVE STATE. Cancel one or more runs/tasks by external id.

No parameter schema in public metadata yet.

replay_runsMUTATES LIVE STATE. Replay/retry one or more runs/tasks by external id.

MUTATES LIVE STATE. Replay/retry one or more runs/tasks by external id.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Configuration

HATCHET_CLIENT_TOKEN*secret

Hatchet API token (a JWT). Encodes the server URL and tenant, so it is normally the only setting required.

HATCHET_API_BASE

Override the API base URL. Self-hosters can point this at any Hatchet instance.

HATCHET_TENANT_ID

Override the tenant id decoded from the token.

Readme

hatchet-mcp

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.

Install

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.

Configuration

View the full README on GitHub

Details

Repository: github.com/elliotpadfield/hatchet-mcp
Categories: AI & LLM Tools, Automation & Workflows
Package: hatchet-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

1

Evermint Mcpevermint-app/evermint-mcpMint tamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.1stars

2

Fabric Marketplacefabric-protocol/fabricAgent-native marketplace. Bootstrap, list inventory, search, negotiate, and trade via MCP.1stars

3

Openpaper Mcpfedericodeponte/openpaper-mcpAutonomous research engine: auto research from a prompt to a fully-cited academic paper via MCP1stars

4

MCPBridgeiamjrmh/mcpbridgeUnified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender.1stars

5

ARPintuition-box/arpCheck a skill, MCP server or agent before your agent installs or pays it. Reads only.1stars

6

Imperium Manifoldimperiumcore/manifoldLightning-gated Cohereon Doctrine v6.1. 398 components, tiered pricing, agent onboarding.1stars