Claude-FAF-MCP

Official MCP server for .FAF (Foundational AI-context Format) with 50 tools - Persistent project context that integrates seamlessly with Claude Desktop workflows

---

🏁 AI-Readiness Scorecard

The closer you get to 100% the better AI can assist you.

At 55% you are building your project with half a blueprint and basically flipping a coin with AI. .FAF defines, and AI becomes optimized for Context with the project.faf file.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🏎️  FAF AI-READINESS SCORE: 100/100 — PODIUM EDITION
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📊 CORE INTELLIGENCE                    🎯 CONTEXT DELIVERY
├─ Project DNA            [██████] 100%  ├─ MCP Protocol      [██████] 100%
├─ Architecture Map       [██████] 100%  ├─ 50 Native Tools   [██████] 100%
├─ Domain Model          [██████] 100%  ├─ IANA Format       [██████] 100%
└─ Version Tracking      [██████] 100%  └─ Universal Context [██████] 100%

🚀 PERFORMANCE                          ⚡ STANDALONE OPERATION
├─ 16.2x CLI Speedup     [██████] 100%  ├─ Zero Dependencies [██████] 100%
├─ 19ms Avg Execution    [██████] 100%  ├─ Bundled Engine    [██████] 100%
├─ 50/50 Tools Active    [██████] 100%  ├─ Direct Function   [██████] 100%
└─ Zero Memory Leaks     [██████] 100%  └─ 14 Bundled Cmds   [██████] 100%

🏆 project.faf score: podium
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

---

⚡ Quick Start

Copy and paste this to Claude/your AI:

Install the FAF MCP server: npm install -g claude-faf-mcp, then add this to my claude_desktop_config.json: {"mcpServers": {"faf": {"command": "npx", "args": ["-y", "claude-faf-mcp"]}}} and restart Claude Desktop.

One-Click Alternative: Desktop Extension (.mcpb)

---

🎯 What is FAF?

The .FAF Position in the MCP Ecosystem:

  Model        Context          Protocol
  ─────        ───────          ────────
  LLM       →   IANA Format →    Open Protocol
  Claude   →   .faf        →    MCP
  Gemini   →   .faf        →    MCP
  Codex    →   .faf        →    MCP

.FAF is the foundational, universal base layer for any Model using the MCP Protocol. It provides the standardized Context that makes the Model Context Protocol work for everyone.

---

🛠️ Core Features

51 MCP Tools (100% Standalone)

• faf_quick - Lightning-fast project.faf creation (3ms avg)
• faf_enhance - Intelligent enhancement with auto-detection
• faf_read - Parse and validate FAF files
• faf_write - Create/update FAF with validation
• faf_score - AI-readiness scoring engine
• faf_compress - Intelligent size optimization
• 14 bundled commands - Zero CLI dependencies, 16.2x faster

IANA-Registered Standard

• Official MIME type: application/vnd.faf+yaml
• W3C-compliant structured format
• Universal AI context protocol
• Cross-platform compatibility

Championship Performance

• 16.2x faster than CLI versions (direct function calls vs process spawning)
• 19ms average execution across all bundled commands
• Fastest: 1ms (formats command)
• Zero memory leaks with F1-grade engineering

---

📚 Documentation

• CHANGELOG - Version history and release notes
• Full Documentation - Complete guide
• FAQ - Common questions
• Getting Started - Installation & setup
• MCP Tools Reference - All 50 tools
• Website - faf.one
• Discord Community - Join the discussion

---

🏆 Why FAF?

"README for the AI era" — Gemini CLI

Persistent Context - Your project's DNA lives in project.faf, readable by any AI or human

Universal Format - IANA-registered standard works across Claude, Gemini, Codex, any LLM

Zero Setup Tax - One file (project.faf) eliminates AI context setup across your entire team

Championship Engineering - F1-inspired performance with strict TypeScript, zero runtime errors

---

📦 Ecosystem

• FAF Format Spec - Official IANA specification
• FAF CLI - Command-line tooling
• Chrome Extension - Browser integration
• faf.one - Official website and documentation

---

📄 License

MIT License - Free and open source

---

Built with F1-inspired engineering principles 🏎️⚡

"It's so logical if it didn't exist, AI would have built it itself" — Claude