Claude Faf Mcp

Claude Faf Mcp

What is Claude Faf Mcp about?

Claude Faf Mcp delivers a persistent AI‑readiness layer by storing project metadata in an IANA‑registered .faf format (application/vnd.faf+yaml). The server continuously bi‑syncs this file with CLAUDE.md, ensuring that every AI session starts with the full, up‑to‑date project DNA.

How to use Claude Faf Mcp?

1. Install globally: npm install -g claude-faf-mcp.
2. Add the MCP server definition to your Claude Desktop configuration:

   {"mcpServers": {"faf": {"command": "npx", "args": ["-y", "claude-faf-mcp"]}}}
   

3. Restart Claude Desktop.
4. Use any of the 52 bundled MCP tools (faf_init, faf_score, faf_sync, faf_sixws, etc.) via the CLI or within Claude prompts to initialise, score, and sync context.

Key features of Claude Faf Mcp

• Eternal bi‑sync: .faf ↔ CLAUDE.md updates propagate in ~8 ms.
• AI‑Readiness scoring: faf_score returns a 0‑100 % readiness gauge (Gold Code at 100 %).
• 52 standalone tools: fast, dependency‑free commands (average 19 ms, fastest 1 ms).
• 6Ws Builder: interactive form or CLI (faf 6ws) to capture WHO/WHAT/WHERE/WHY/WHEN/HOW and boost readiness by 25‑35 %.
• Auto‑extract from README: faf_readme parses existing documentation into context fields.
• Cross‑LLM compatibility: works with Claude, Gemini, Codex, Grok, Cursor, etc.
• IANA‑registered MIME type: application/vnd.faf+yaml ensures standards compliance.
• Zero manual maintenance: single source of truth eliminates drift across branches and teams.

Use cases of Claude Faf Mcp

• On‑boarding new developers – instantly provide the full project DNA, removing repetitive knowledge transfer.
• Long‑running codebases – preserve architectural decisions and domain models for years without loss.
• Multi‑model deployments – feed the same context to Claude, Gemini, or any custom LLM via the MCP.
• CI/CD pipelines – run faf_score during builds to enforce a minimum AI‑readiness threshold.
• Documentation generation – leverage faf_readme to keep README and .faf in sync automatically.

FAQ from the Claude Faf Mcp

Q: Do I need to run a separate server process? A: No. The MCP server is launched on‑demand via the npx -y claude-faf-mcp command configured in Claude Desktop.

Q: Can I use the tools without Claude Desktop? A: Yes. All 52 tools are CLI‑only and can be invoked directly from a terminal.

Q: Is the .faf format proprietary? A: It is an open, IANA‑registered YAML format (application/vnd.faf+yaml).

Q: How does scoring work? A: faf_score evaluates completeness of the six‑question fields, presence of architecture diagrams, domain models, and other metadata, returning a percentage.

Q: What if I already have a comprehensive README? A: Use faf_readme to auto‑extract the six‑question context; you can merge or overwrite existing .faf fields.

Q: Are there any runtime dependencies? A: The tools are self‑contained; no external CLI utilities are required.

.FAF optimizes AI for your codebase. At 100% (Gold Code), AI stops guessing and starts knowing. Live bi-sync between .faf ↔ CLAUDE.md means zero context-drift — your project DNA stays aligned with AI, forever.

---

The Problem: Context-Drift

AI assistants forget. They misunderstand. They drift.

Every new session, every new file, every new developer — AI starts guessing again. Your codebase context leaks away. Yesterday's perfect assistant becomes today's confused intern.

.FAF fixes this permanently.

---

The Solution: Gold Code

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🏆  FAF AI-READINESS SCORE: 100/100 — GOLD CODE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

At 100%, AI is optimized. No more guessing.
Peak AI performance activated.

├─ Project DNA locked in        ├─ Zero context-drift
├─ Architecture understood      ├─ Eternal bi-sync active
├─ Domain model captured        ├─ Team alignment permanent
└─ Every session starts smart   └─ AI works WITH you, not around you

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Gold Code = AI Optimized. Your project DNA lives in project.faf. AI reads it instantly. Context never drifts.

---

🔄 Eternal Bi-Sync

The magic: .faf ↔ CLAUDE.md stay synchronized in milliseconds.

project.faf  ←──── 8ms ────→  CLAUDE.md
     │                            │
     └── Single source of truth ──┘

• Update either file → both stay aligned
• Zero manual maintenance
• Works across teams, branches, sessions
• Context never goes stale

---

Tier System: From Blind to Optimized

Tier	Score	Status
🏆 Trophy	100%	AI Optimized — Gold Code
🥇 Gold	99%+	Near-perfect context
🥈 Silver	95%+	Excellent
🥉 Bronze	85%+	Production ready
🟢 Green	70%+	Solid foundation
🟡 Yellow	55%+	AI flipping coins
🔴 Red	<55%	AI working blind
🤍 White	0%	No context at all

At 55%, AI is guessing half the time. At 100%, AI is optimized.

---

💎 Lifecycle Value

Setup savings get you started. Lifecycle optimization keeps you ahead.

When	Without FAF	With FAF
Day 1	20 min setup per dev	0 min — instant context
Month 1	AI forgets between sessions	AI remembers everything
Year 1	New devs re-explain everything	New devs inherit full context
Year 3+	Institutional knowledge lost	Project DNA preserved forever

Setup savings: 20 minutes. Lifecycle savings: Infinite.

---

⚡ 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)

---

🛠️ 52 MCP Tools

All tools run standalone — zero CLI dependencies, 16.2x faster than process spawning.

Tool	Purpose
faf_init	Initialize project DNA
faf_score	Check AI-readiness (0-100%)
faf_sync	Bi-sync .faf ↔ CLAUDE.md
faf_auto	Auto-detect and populate context
faf_enhance	Intelligent enhancement
faf_quick	Lightning-fast creation (3ms)
faf_readme	Extract 6 Ws from README (+25-35% boost)
faf_sixws	NEW: 6Ws Builder - Interactive web form + CLI integration
faf_human_add	Add human context (Claude Code compatible)

Performance: 19ms average execution. Fastest: 1ms.

✨ New in v4.3.0: 6Ws Builder

Answer 6 questions to create AI-ready context:

1. WHO - Who is this for?
2. WHAT - What does it do?
3. WHERE - Where does it run?
4. WHY - Why does it exist?
5. WHEN - When to use it?
6. HOW - How to get started?

Complete Workflow in Claude Desktop:

User → Claude: "Help me add context to my project"
Claude → User: "Visit faf.one/6ws to fill out the 6 questions"
User → Fills form → Copies human_context YAML
User → Claude: [Pastes YAML]
Claude → Uses faf_human_add tool → Context merged!
Claude → Runs faf_score → Shows new AI-readiness score ✨

Two ways to use:

• Web (Recommended): faf.one/6ws — Fill form, copy YAML, use faf_human_add in Claude
• CLI: faf 6ws — Interactive paste-back workflow (terminal)

Score Boost: Completing all 6 Ws typically adds +25-35% to your AI-readiness score!

Works with Claude, Gemini, Grok, Cursor, Codex, WARP, any AI assistant.

📄 Alternative: Auto-Extract from Existing README

Already have a README.md? Skip the form and extract context automatically:

In Claude Desktop:

User → Claude: "Extract context from my README"
Claude → Uses faf_readme tool → Automatically extracts WHO/WHAT/WHERE/WHY/WHEN/HOW
Claude → Shows extracted context with confidence scores
User → "Merge it!"
Claude → Uses faf_readme { merge: true } → Context added to project.faf
Claude → Runs faf_score → Shows new AI-readiness score ✨

What faf_readme extracts:

• WHAT: Project description, taglines, TL;DR sections
• WHY: Problem statements, benefits, motivation
• WHO: Target audience ("for developers", "built for teams")
• WHERE: Platforms (npm, pip, Docker, cloud, browser)
• WHEN: Status badges, version info, test counts
• HOW: Quick Start commands, installation instructions

Usage:

// Just extract (see what's found)
faf_readme

// Extract and merge into project.faf
faf_readme { merge: true }

// Overwrite existing fields
faf_readme { merge: true, overwrite: true }

Same score boost: +25-35% typical, instant results, zero manual work!

---

🎯 The .FAF Position

  Model        Context          Protocol
  ─────        ───────          ────────
  Claude    →   .faf        →    MCP
  Gemini    →   .faf        →    MCP
  Codex     →   .faf        →    MCP
  Any LLM   →   .faf        →    MCP

.FAF is the foundational layer. Universal context format. IANA-registered (application/vnd.faf+yaml). Works with any AI.

---

📦 Ecosystem

• faf-cli — CLI tool v4.3.0 (21k+ downloads, 671/671 tests passing)
• faf.one/6ws — 6Ws Builder (Web + CLI integration)
• MCPaaS — MCP as a Service (The Endpoint for Context)
• faf-wasm — WASM SDK (<5ms scoring)
• Chrome Extension — Browser integration
• faf.one — Official website

---

📚 Documentation

• Full Documentation
• MCP Tools Reference

---

📄 License

MIT License — Free and open source

---

Zero drift. Eternal sync. AI optimized. 🏆

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