@metago-ai/mcp-server

MetaGO MCP Server —— 智能体运行时控制层套件（驭智层）的 MCP 协议实现。暴露 55 tools + 8 prompts 给任意 MCP 客户端。Engine V2 硬驱动：KMWI 记忆、元进化引擎、技能生成器以真实代码运行，而非 prompt。

基于 Model Context Protocol 标准，通过 stdio 传输与客户端通信。一次配置，即可让 Claude Desktop、Cursor、Trae、ZCode 等任意 MCP 客户端获得元构生命体的决策锁、元进化、KMWI 记忆管理、批判性分析等核心能力。

🌐 官网：https://metago.life · Studio：https://metago.life/studio/

What is this?

This is the MCP Server subpackage of MetaGO Agent Harness. It exposes the Harness's 55 capabilities as MCP tools and 8 guided entry points as MCP prompts, so any MCP-compatible client can plug into the MetaGO lifeform without changing its own code.

Engine V2 — Hard Drive (new in 2.0.0)

Three of the 55 tools are hard-driven by Engine V2 — they call real TypeScript code, not just return prompt guidance:

The other 50 tools return structured guidance (soft drive) that the agent follows within its decision-lock.

Tool count breakdown (55 total)

55 = 22 thinking tools (toolkit-data.ts)
   + 30 core skills  (39 skill folders, 37 exported in skills-data.ts − 7 name-collisions merged into toolkit)
   + 1  event reporter (metago_report_event)

Common mistake: 22 + 38 + 1 = 61. Wrong. The skills directory has 39 folders, but skills-data.ts only exports 39 (missing metago-delivery-gate and metago-discipline, which live in toolkit-data.ts — note: 36.9.4 added metago-first-principles and metago-adversarial-review to skills-data.ts). Then 7 skill names collide with toolkit tools and are merged. So: 22 + (39 − 7) + 1 = 55.

Install

Global install (recommended for npx clients)

npm install -g @metago-ai/mcp-server

Run directly via npx (no install)

npx -y @metago-ai/mcp-server

Local development

git clone https://gitee.com/metago/metagolifeform.git
cd metagolifeform/packages/mcp-server
npm install
npm run build      # TypeScript compile
npm start          # node dist/index.js
npm run dev        # tsx hot-reload

Client configuration

Claude Desktop

Edit claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

{
  "mcpServers": {
    "metago": {
      "command": "npx",
      "args": ["-y", "@metago-ai/mcp-server"]
    }
  }
}

Cursor / Trae / ZCode

Edit the platform's MCP config (.cursor/mcp.json, Trae MCP settings, etc.):

{
  "mcpServers": {
    "metago": {
      "command": "npx",
      "args": ["-y", "@metago-ai/mcp-server"]
    }
  }
}

If globally installed, you can use "command": "@metago-ai/mcp-server" with no args.

Engineering Quality Tools (2)

Core Skills (30, after 7 merges)

Each tool takes an input string (the content/question/code to process).

Cognition (4)

Safeguard (3)

Governance (2)

Evolution (3) — Engine V2 hard-driven

Execution (4)

Traceability (3)

Value (3)

Consciousness / Methodology / Architecture (9)

Memory (1) — Engine V2 hard-driven

Thinking Tools (22)

Planning & Reasoning (5)

Quality & Critique (4)

Value & Ethics (3)

Provenance Labeling (3)

Coupling & Scene (2)

Product Improvement (3) + Delivery Quality (2)

8 Prompts

Technical requirements

• Node.js >= 18.0.0
• ESM module ("type": "module")
• TypeScript strict mode
• Import paths with .js suffix (Node16 moduleResolution)
• @metago-ai/engine ^2.0.0 (for Engine V2 hard drive)

Packages

License

MIT License © 易霄 / MetaGO Lightyear