Claude-FAF-MCP
Only Persistent Project Context MCP Server - Official Anthropic Registry
claude-faf-mcp
Tell AI what you're building, who it's for, and why it matters. 30 seconds. ๐ It never forgets.
33 MCP tools. IANA-registered format (application/vnd.faf+yaml). 2,346 test executions per push.
The 3Ws โ 3 Answers. That's It.
Every great product started with 3 answers to the 3Ws โ Who, What, Why:
| WHO is it for? | WHAT does it do? | WHY build it? | |
|---|---|---|---|
| Uber | People who need a ride | Tap a button, car arrives | Taxis were broken |
| Airbnb | Travelers who can't afford hotels | Stay in someone's spare room | Millions of empty rooms exist |
| Slack | Teams drowning in email | Organized group messaging | Decisions buried in threads |
| Venmo | Friends splitting bills | Send money instantly | Someone always forgets to pay back |
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 โ For Optimized AI
3Ws gets you started. For fully optimized AI, complete the set โ 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 โ faf.one/ideas
Quick Start
Copy and paste this 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.
Then tell Claude your 3Ws: "I'm building [what] for [who] because [why]"
How It Works
You โ 3 answers โ project.faf โ AI reads it โ every session โ forever
project.faf โโโ 8ms โโโ CLAUDE.md (bi-sync, free)
project.faf โโโ 8ms โโโ MEMORY.md (tri-sync, Pro ๐)
Claude does the rest. Zero-effort, right first time, fast, accurate, done. Language, framework, package manager, build tools โ all auto-detected from your existing files. The human context is the part only you can give.
Scoring: From Blind to Optimized
| Tier | Score | What it means |
|---|---|---|
| ๐ Trophy | 100% | Gold Code โ AI is optimized |
| ๐ฅ Gold | 99%+ | Near-perfect context |
| ๐ฅ Silver | 95%+ | Excellent |
| ๐ฅ Bronze | 85%+ | Production ready |
| ๐ข Green | 70%+ | Solid foundation |
| ๐ก Yellow | 55%+ | AI flipping coins |
| ๐ด Red | <55% | AI working blind |
| ๐ค White | 0% | No context at all |
At 55%, AI guesses half the time. At 100%, AI knows your project. Same compiler as faf-cli โ same score everywhere.
33 MCP Tools
All tools run standalone โ zero CLI dependencies, 19ms average execution.
Create & Detect
| Tool | Purpose |
|---|---|
faf_init | Initialize project DNA |
faf_auto | Auto-detect stack and populate context |
faf_quick | Lightning-fast creation (3ms) |
faf_readme | Extract context from README (+25-35% boost) |
faf_formats | Discover all formats in your project |
faf_git | Extract context from any GitHub repo URL |
faf_human_add | Add human context (the 6Ws) |
Validate & Score
| Tool | Purpose |
|---|---|
faf_score | AI-readiness score (0-100%) with breakdown |
faf_check | Validate .faf structure |
faf_doctor | Diagnose and fix common issues |
faf_go | Guided interview to Gold Code |
Sync & Persist
| Tool | Purpose |
|---|---|
faf_sync | Sync .faf โ CLAUDE.md |
faf_bi_sync | Bi-directional .faf โ CLAUDE.md |
faf_tri_sync | Tri-sync to MEMORY.md (Pro โ 14-day free trial) |
faf_enhance | Intelligent enhancement |
Export & Interop
| Tool | Purpose |
|---|---|
faf_agents | Import/export AGENTS.md (OpenAI Codex) |
faf_cursor | Import/export .cursorrules (Cursor IDE) |
faf_gemini | Import/export GEMINI.md (Google Gemini) |
faf_conductor | Import/export Conductor directory |
Read & Write
| Tool | Purpose |
|---|---|
faf_read | Read any file |
faf_write | Write any file |
faf_status | Project status overview |
faf_debug | Environment inspection |
faf_about | What is .faf? |
๐ Nelly Never Forgets (Pro)
bi-sync keeps .faf โ CLAUDE.md aligned. Free forever.
tri-sync adds MEMORY.md โ your AI remembers across sessions. Feed Nelly, she never forgets.
bi-sync = .faf โ CLAUDE.md โ free forever
tri-sync = .faf โ CLAUDE.md โ MEMORY.md โ Pro ๐
$3/mo ยท $19/yr ยท $29/yr Global. 14-day free trial, no signup. Friends of FAF โ faf.one/pro
The .FAF Position
Model Context Protocol
โโโโโ โโโโโโโ โโโโโโโโ
Claude โ .faf โ MCP
Gemini โ .faf โ MCP
Codex โ .faf โ MCP
Any LLM โ .faf โ MCP
IANA-registered (application/vnd.faf+yaml). Works with any AI. Define once, use everywhere.
Ecosystem
| Package | Platform | Registry |
|---|---|---|
| claude-faf-mcp (this) | Claude | npm |
| faf-cli | Universal CLI | npm + Homebrew |
| gemini-faf-mcp | Google Gemini | PyPI |
| grok-faf-mcp | xAI Grok | npm |
| rust-faf-mcp | Rust | crates.io |
| faf-wasm | Browser/Edge | npm |
| Chrome Extension | Browser | Chrome Web Store |
Same project.faf. Same scoring. Same result. Different execution layer.
Quality
391 tests ยท 12 suites ยท 6 platforms (ubuntu/macos/windows ร Node 18/20)
Privacy
Everything runs locally. No data leaves your machine. No analytics, no telemetry, no tracking, no accounts. Privacy policy โ
License
MIT โ Free and open source
.faf is the format.
project.fafis the file. 100% is Gold Code.
"It's so logical if it didn't exist, AI would have built it itself" โ Claude
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Math MCP Learning
Educational MCP server with math operations, statistics, visualizations, and persistent workspace.
Google Workspace Developers
Developer documentation for Google Workspace APIs
ContextForge
Persistent memory MCP server for Claude โ store decisions, code, and knowledge across sessions.
Sentry
Official MCP server for Sentry.
secretctl
AI-safe secrets manager - inject credentials as env vars, AI never sees plaintext
agent smith
Auto-generate AGENTS.md from your codebase
Apache SkyWalking MCP
An MCP server for integrating AI agents with the SkyWalking observability platform and its ecosystem.
MCP Builder
A Python-based server to install and configure other MCP servers from PyPI, npm, or local directories.
MCP Terminal
An MCP server for accessing the terminal and managing git repositories.
AI Image Generation
Generate images using the Together AI API. Supports custom aspect ratios, save paths, and batch generation.