Tetrad MCP Server

Most developer tooling work still happens through a UI a human drives. Tetrad MCP server moves it into the conversation instead. Quadruple consensus MCP server for code validation using Codex, Gemini, and Qwen.

The short version

The system implements a quadruple consensus protocol where no code or plan is accepted without approval from four intelligences: the three external evaluators + Claude Code itself.

• Quadruple Consensus — 4 AI models must agree to approve code
• ReasoningBank — Continuous learning system with RETRIEVE→JUDGE→DISTILL→CONSOLIDATE cycle
• High Performance — Written in Rust with parallel execution via Tokio
• MCP Server — JSON-RPC 2.0 server over stdio for Claude Code integration
• Full CLI — Intuitive commands (init, serve, status, doctor, config, etc.)
• LRU Cache — Result caching with configurable TTL

The tools it exposes

The server publishes 6 tools. What each one is for:

• tetrad_review_plan — Review implementation plans before coding
• tetrad_review_code — Review code before saving
• tetrad_review_tests — Review tests before finalizing
• tetrad_confirm — Confirm agreement with received feedback
• tetrad_final_check — Final verification before commit
• tetrad_status — Check health of evaluators

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, GOOGLE_API_KEY, DASHSCOPE_API_KEY, GEMINI_API_KEY, OPENAI_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

To use Tetrad, you need at least one of the AI CLIs installed and authenticated: | CLI | Installation | Auth Without API Key? | Free Tier | |-----|--------------|----------------------|-----------| | Codex CLI | npm i -g @openai/codex | ✅ ChatGPT Plus/Pro/Business | Via subscription | | Gemini CLI | `npm i -g

Getting it running

@samoradc/tetrad on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Tetrad's toolset — tetrad_review_plan, tetrad_review_code, tetrad_review_tests and 3 more — is a fair guide to whether it matches your workflow. It is maintained by SamoraDC; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.