Clawwork
Wire Claude Code or Cursor into ClawWork so your agent can manage task boards, track progress, and pull cost reports for a scoped project.
Overview
ClawWork MCP is a MCP server for the Build phase that exposes ClawWork task boards, progress tracking, and cost reporting to your agent via stdio.
What is this MCP server?
- 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
- Package @clawwork/mcp version 0.1.3
- Transport: stdio
- 2 environment variables documented (1 required secret API key)
What problem does it solve?
Agent work disappears into conversation logs with no shared board, milestones, or cost visibility for the project you are shipping.
Who is it for?
Solo builders using ClawWork who want their agent to maintain task boards and cost summaries without leaving the IDE.
Skip if: Teams not on ClawWork or builders who only need local TODO files with no external PM API.
What do I get? / Deliverables
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
Recommended MCP Servers
Journey fit
Project boards and delivery tracking sit in the build phase when you are actively shipping features with an AI agent as a teammate. ClawWork is explicitly AI agent project management—task boards, progress, and cost reporting map to PM subphase tooling for solo builders orchestrating agent work.
How it compares
ClawWork API bridge via MCP—not a generic agent skill or a full planning framework.
Common Questions / FAQ
Who is ClawWork MCP for?
Indie 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.