🏎️ CLAUDE.md - claude-faf-mcp Persistent Context & Intelligence

.faf format | project.faf

PROJECT STATE: ACTIVE 🚀

Current Position: Provide FAF context tools directly in Claude Desktop via MCP Tyre Compound: ULTRASOFT C5 (Maximum Performance)

🎨 CORE CONTEXT

Project Identity

• Name: claude-faf-mcp
• Stack: Node.js/TypeScript
• Quality: F1-INSPIRED (Championship Performance)

Our Mission - 100% Standalone MCP Server

v3.0.4 Historic Milestone: ZERO CLI DEPENDENCIES

claude-faf-mcp: 100% STANDALONE
├── 32/32 MCP tools operational
├── 14/14 bundled commands
├── 16.2x faster than CLI versions
├── 19ms average execution
└── Zero external dependencies

CRITICAL: claude-faf-mcp IS NOT A WRAPPER

• ✅ Independent standalone MCP server
• ✅ 100% operational without any CLI
• ✅ Own bundled FAF engine
• ✅ Championship-grade performance
• ❌ NOT a wrapper, NOT dependent on CLI

The .faf Position in MCP:

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

.FAF provides the standardized Context that makes the Model Context Protocol work for everyone.

Technical Architecture

• What Building: Universal FAF MCP Server for Claude Desktop - AI Context Intelligence
• Main Language: TypeScript

📊 Context Quality Status

• Overall Assessment: Good
• Test Coverage: 391/391 passing (12 test suites, 6 platforms)
• CI Matrix: ubuntu/macos/windows × Node 18.x/20.x — all green
• Last Updated: 2026-03-10

🚨 CODE CHANGE PROTOCOL - MANDATORY 🚨

CRITICAL RULE: DO NOT WRITE CODE UNLESS EXPLICITLY AUTHORIZED

Before making ANY code changes:

1. DESCRIBE what you plan to change
2. WAIT for explicit approval ("GO!", "YES", "Do it")
3. ONLY THEN write the code

What counts as "code changes":

• Adding new features
• Modifying existing functionality
• Changing user-facing text/messages
• Adding branding, emojis, or styling
• Refactoring

What does NOT need approval:

• Reading files to answer questions
• Running tests
• Checking versions
• Research and exploration

Why this matters:

• The F1 hallucination incident (v3.3.3) showed AI adding unauthorized branding
• User-facing output must be controlled by wolfejam
• Trust requires permission-based coding

🚨 NPM PUBLISH PROTOCOL - MANDATORY 🚨

CRITICAL RULE: npm publish IS FORBIDDEN WITHOUT APPROVAL

Before ANY npm publish of claude-faf-mcp (or any FAF package):

1. Follow the MCP Publish Checklist at /Users/wolfejam/FAF-GOLD/PLANET-FAF/PUBLISH-PROTOCOL.md
2. Run ALL checklist items (build, tests, version, README, CHANGELOG, SKILL.md, etc.)
3. Request approval with checklist results in the format specified
4. Wait for OFFICIAL GO! from wolfejam

Required approval signals:

• ✅ "GO!" - Approved to publish
• ✅ "GREEN LIGHT" - Approved to publish
• ❌ Anything else - DO NOT PUBLISH

Why this matters:

• Trust is everything
• Production infrastructure for 13k+ developers
• Official Anthropic MCP steward responsibility
• One bad publish can damage reputation permanently

No exceptions. No shortcuts. Professional. Boring. Trusted.

STATUS: BI-SYNC ACTIVE 🔗 - Synchronized with .faf context!

Last Sync: 2026-03-04T07:28:12.365Z Sync Engine: F1-Inspired Software Engineering 🏎️⚡️_championship_sync

claude-faf-mcp

Tell AI what you're building, who it's for, and why it matters. 30 seconds. 🐘 It never forgets.

FAF defines. MD instructs. AI codes.

🐘 tri-sync now free for all builders — .faf ↔ CLAUDE.md ↔ MEMORY.md in one command. Pro feature. Now free.

⚡ New: /faf prompt — type /faf in Claude Desktop. It checks your project, scores it, drives it to 100%, and syncs. Relentlessly. One command.

32 MCP tools. 1 prompt. IANA-registered format (application/vnd.faf+yaml). 2,346 test executions per push.

The 3Ws — 3 Answers. That's It.

Every great product started with 3 answers to the 3Ws — Who, What, Why:

Same pattern. Every product that works starts here. .faf captures it:

human_context:
  who: "people who need a ride across town"
  what: "tap a button, car arrives in minutes"
  why: "taxis are slow, expensive, and hard to find"

30 seconds. Claude builds your project.faf from this. Every session after, AI starts smart.

The 6Ws — For Optimized AI

3Ws gets you started. For fully optimized AI, complete the set — Where, When, How:

  where: "mobile app, iOS and Android"    # where does it live?
  when: "launch in 3 months"              # when is it shipping?
  how: "GPS matching, real-time pricing"  # how does it work?

3Ws initiates the project with AI. 6Ws optimizes AI to 100%. Same YAML, same file. More examples → faf.one/ideas

Quick Start

One-click install — Claude Desktop

⬇ Download claude-faf-mcp-5.5.1.mcpb

Double-click the downloaded file. Claude Desktop installs it automatically. No terminal. No JSON config. 32 tools live in 10 seconds.

Or — copy-paste to Claude

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.

Or — manual npm install

npm install -g claude-faf-mcp

Add to claude_desktop_config.json:

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

Restart Claude Desktop.

Then

Type /faf — Claude checks your project, scores it, drives it to 100%, and syncs. Done.

Or tell Claude your 3Ws: "I'm building [what] for [who] because [why]"

How It Works

You → 3 answers → project.faf → AI reads it → every session → forever

project.faf  ←── 8ms ──→  CLAUDE.md     (bi-sync, free)
project.faf  ←── 8ms ──→  MEMORY.md     (tri-sync, Pro 🐘)

Claude does the rest. Zero-effort, right first time, fast, accurate, done. Language, framework, package manager, build tools — all auto-detected from your existing files. The human context is the part only you can give.

Scoring: From Blind to Optimized

At 55%, AI guesses half the time. At 100%, AI knows your project. Same compiler as faf-cli — same score everywhere.

32 MCP Tools

All tools run standalone — zero CLI dependencies, 19ms average execution.

Create & Detect

Validate & Score

Sync & Persist

Export & Interop

Read & Write

Full tool reference →

🐘 Nelly Never Forgets

bi-sync keeps .faf ↔ CLAUDE.md aligned.

tri-sync adds MEMORY.md — your AI remembers your project across every session.

bi-sync  = .faf ↔ CLAUDE.md              ← always in sync
tri-sync = .faf ↔ CLAUDE.md ↔ MEMORY.md  ← Nelly never forgets 🐘

Pro feature, free for developers. Teams & Enterprise: faf.one/pro (plans)

The .FAF Position

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

IANA-registered (application/vnd.faf+yaml). Works with any AI. Define once, use everywhere.

Ecosystem

Same project.faf. Same scoring. Same result. Different execution layer.

Quality

391 tests · 12 suites · 6 platforms (ubuntu/macos/windows × Node 18/20)

CI Dashboard →

Privacy

Everything runs locally. No data leaves your machine. No analytics, no telemetry, no tracking, no accounts. Privacy policy →

If claude-faf-mcp has been useful, consider starring the repo — it helps others find it.

License

MIT — Free and open source

FAF Family

format | driven 🏎️⚡️ wolfejam.dev

Get the CLI

faf-cli — The original AI-Context CLI. A must-have for every builder.

npx faf-cli auto

Anthropic MCP #2759 · IANA Registered: application/vnd.faf+yaml · faf.one · npm