worker-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@worker-mcpRefactor the main function in src/app.py to use async/await"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
worker-mcp
一个 stdio MCP server,让 Claude Code(或任何 MCP 客户端)把编码任务委派给一个 worker CLI 执行。调用方(Claude)只做计划、监督和验收,worker 负责所有实际的 代码修改和命令执行。
原理
server 通过子进程调用 <worker-cli> -p <prompt> --output-format stream-json(无头模式),
解析其 stream-json 输出,把 worker 的最终回复和 session_id 返回给调用方。
默认 worker 是 Kimi Code CLI(kimi),可通过环境变量 WORKER_CLI_BIN 换成任何
兼容同一 CLI 契约的执行器:支持 -p 无头执行、-S <id> / -c 会话续接,
并以 stream-json 逐行输出 role=assistant(回复)和 role=meta(session_id)事件。
注意:worker 无头模式会自动批准所有工具调用(等同于 yolo),
可以在指定 cwd 内自由读写文件、执行命令。请只把可信的项目目录传给 cwd。
Related MCP server: Cursor Delegate
工作模式:Claude 监督计划,worker 执行
server 在 MCP instructions 和工具描述中写明了分工,Claude Code 连接后会自动遵循:
Claude(监督/计划):拆解目标、决定步骤顺序、为每步编写自包含任务书 (背景、涉及文件、改什么、验收标准——worker 看不到 Claude 的上下文)、 验收每步结果(读文件/diff、让 worker 跑测试)、失败时用
worker_continue打回重修。worker(执行):在指定
cwd内完成所有实际的代码修改和命令执行。
Claude 被引导不自己调用 Edit/Write 等工具改代码(软引导,非强制拦截)。
工具
工具 | 说明 |
| 在 |
| 对既有会话追加指令;不传 |
安装
项目内已用 uv 管理独立 Python 3.12(不依赖系统 Python):
# 如需从零重建环境:
curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="$PWD/.tools" INSTALLER_NO_MODIFY_PATH=1 sh
UV_PYTHON_INSTALL_DIR="$PWD/.tools/python" .tools/uv venv --python 3.12 .venv
.tools/uv pip install --python .venv/bin/python "mcp>=1.0"注册到 Claude Code
claude mcp add worker -- /Users/quinlanhoo/Code/KIMI-MCP/KIMI-MCP/.venv/bin/python /Users/quinlanhoo/Code/KIMI-MCP/KIMI-MCP/server.py之后在 Claude Code 中即可通过 worker_run / worker_continue 工具把任务交给 worker。
配置
环境变量 | 默认 | 说明 |
|
| worker CLI 路径(须兼容上述 CLI 契约) |
|
| 默认超时秒数(工具参数可单独覆盖) |
This server cannot be deployed
Maintenance
Related MCP Connectors
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
Hand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables ISLI agents and MCP clients to dispatch natural-language coding and terminal tasks to a locally-installed Claude Code CLI, supporting both one-shot execution and persistent sessions with workspace and security controls.-
- AlicenseAqualityAmaintenanceEnables MCP clients like Claude Code and Codex to delegate coding tasks to Cursor's CLI agent, which implements changes in the workspace and returns clean, structured results for review.3133 npm4MIT
- AlicenseNot gradedqualityBmaintenanceEnables Codex to delegate bounded engineering jobs to Claude Code CLI in isolated Git worktrees with strict security and allowance pacing.MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code to delegate implementation tasks to Antigravity CLI and OpenCode, run them fully autonomously, and then review and gate the results.MIT