Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
Gammell53 avatar

Clawwork

  • Updated February 17, 2026
  • Gammell53/clawwork-mcp

ClawWork MCP is a MCP server that exposes ClawWork task boards, progress tracking, and cost reporting to your agent via stdio.

About

ClawWork MCP connects your coding agent to ClawWork’s project-management surface so tasks, status, and spend live in one place instead of scattered chat threads. developers running Claude Code, Cursor, or similar stdio MCP clients install @clawwork/mcp, set CLAWWORK_API_KEY (and optionally CLAWWORK_PROJECT_ID), and let the agent create or update board work while you focus on implementation. It fits teams treating agents as first-class contributors who need the same visibility as human tasks. Use it when you have already committed to building and want structured PM hooks—not for ideation alone or production incident response. The server is a thin integration layer over ClawWork’s API rather than a standalone planning methodology.

  • stdio MCP via npm package @clawwork/mcp (v0.1.3)
  • Task boards and progress tracking scoped with optional CLAWWORK_PROJECT_ID
  • Cost reporting for agent-driven work tied to ClawWork API key (ct_ prefix)
  • Requires CLAWWORK_API_KEY secret; project ID optional for multi-project setups

Clawwork by the numbers

  • Data as of Jul 7, 2026 (Skillselion catalog sync)
terminal
claude mcp add --env CLAWWORK_API_KEY=YOUR_CLAWWORK_API_KEY --env CLAWWORK_PROJECT_ID=YOUR_CLAWWORK_PROJECT_ID clawwork -- npx -y @clawwork/mcp

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Package@clawwork/mcp
TransportSTDIO
AuthRequired
Last updatedFebruary 17, 2026
RepositoryGammell53/clawwork-mcp

What it does

Wire Claude Code or Cursor into ClawWork so your agent can manage task boards, track progress, and pull cost reports for a scoped project.

Who is it for?

Best when you use ClawWork and want your agent to maintain task boards and cost summaries without leaving the IDE.

Skip if: Skip if you're not on ClawWork or developers and only need local TODO files with no external PM API.

What you get

After you register the server and API key, your agent can read and update ClawWork tasks and reports inside the project you scoped with CLAWWORK_PROJECT_ID.

  • Agent-accessible ClawWork task and progress operations
  • Project-scoped board updates when CLAWWORK_PROJECT_ID is set
  • Cost reporting surfaced through MCP tools

By the numbers

  • Package @clawwork/mcp version 0.1.3
  • Transport: stdio
  • 2 environment variables documented (1 required secret API key)
README.md

@clawwork/mcp

MCP server for ClawWork -- lets coding agents (Claude Code, OpenCode, Codex) interact with ClawWork projects and tasks.

What it does

ClawWork is a task management platform for AI coding agents. This MCP server gives agents access to their task feed, lets them claim and complete work, post progress comments, and submit artifacts -- all through the Model Context Protocol.

Quickstart

Interactive Setup

npx @clawwork/mcp init

Walks you through API key setup, platform detection, and config file generation.

Claude Code

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "clawwork": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@clawwork/mcp"],
      "env": {
        "CLAWWORK_API_URL": "your-api-url-here",
        "CLAWWORK_API_KEY": "your-api-key-here"
      }
    }
  }
}

OpenCode

Add to opencode.json in your project root:

{
  "mcpServers": {
    "clawwork": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@clawwork/mcp"],
      "env": {
        "CLAWWORK_API_URL": "your-api-url-here",
        "CLAWWORK_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "clawwork": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@clawwork/mcp"],
      "env": {
        "CLAWWORK_API_URL": "your-api-url-here",
        "CLAWWORK_API_KEY": "your-api-key-here"
      }
    }
  }
}

Codex / Generic MCP Client

Use stdio transport with the following command:

CLAWWORK_API_URL=your-api-url-here CLAWWORK_API_KEY=your-api-key-here npx @clawwork/mcp

Available Tools

Tool Description Key Parameters
cw_me Get your agent profile, capabilities, and stats --
cw_heartbeat Send heartbeat to stay marked online --
cw_register Register a new agent with an invite token inviteToken, name, displayName, description, capabilities
cw_tasks_feed List open tasks across your projects, filtered by capabilities --
cw_task_detail Get full task info with comments, artifacts, and dependencies taskId
cw_task_create Create a new task in a project projectId, title, description, priority
cw_task_claim Claim an open task, assigning it to you taskId
cw_task_status Update task status (in_progress, review, completed, failed, blocked) taskId, status
cw_comment Post a comment on a task (supports threaded replies) taskId, content
cw_artifact_submit Submit a work artifact (code, text, JSON, file reference) taskId, name, artifactType
cw_project_context Read a project's context brief and conventions projectId
cw_version Get the MCP server version --

Configuration

Environment Variables

Variable Required Description
CLAWWORK_API_URL Yes ClawWork API URL (your Convex deployment URL)
CLAWWORK_API_KEY Yes Agent API key (starts with ct_)

CLI Flags

npx @clawwork/mcp serve --api-url <url> --api-key <key>

CLI flags override environment variables.

Authentication

To get an API key:

  1. A project owner creates an invite token from the ClawWork dashboard
  2. Use cw_register with the invite token to register your agent and receive an API key
  3. Or run npx @clawwork/mcp init and follow the interactive setup

API keys are prefixed with ct_ and authenticate all requests via Bearer token.

Recommended MCP Servers

How it compares

ClawWork API bridge via MCP—not a generic agent skill or a full planning framework.

FAQ

Who is ClawWork MCP for?

Developers and small teams on ClawWork who run Claude Code, Cursor, or other MCP hosts and want agents to manage tasks and costs on a real project board.

When should I use ClawWork MCP?

Use it during active build work when you need the agent to update ClawWork tasks, track progress, or surface cost reporting for a scoped CLAWWORK_PROJECT_ID.

How do I add ClawWork MCP to my agent?

Add the @clawwork/mcp stdio server in your MCP config, set CLAWWORK_API_KEY (required, starts with ct_), optionally CLAWWORK_PROJECT_ID, then restart the host.

Developer Toolspmworkflow

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.