convez.ai
MCP ServerProdutividadeIntermediário
Wolfe-Jam

Claude FAF MCP

Wolfe-Jam/claude-faf-mcp

Contexto de projeto persistente e sincronizado para Claude com formato .faf padronizado

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que oferece contexto persistente de projeto para Claude através do formato .faf (IANA-registrado). Fornece 33 ferramentas para sincronizar e manter coerência entre arquivo de projeto FAF, documentação em Markdown e memória do agente, permitindo que o modelo retenha contexto estruturado entre sessões.

Instalação

$npx convez-ai Wolfe-Jam/claude-faf-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
23
Forks
8
Acompanhando
1
Saúde
100%
Último commit
há 2 dias
Versão
v7.2.1
Issues abertas
1
Contribuidores
3

Casos de uso

  • Manter contexto consistente de projetos longos entre múltiplas conversas com Claude
  • Sincronizar definição de projeto (Who/What/Why) com documentação técnica e memória de agente
  • Gerar e validar scores FAF de projetos com métricas determinísticas e padronizadas
  • Implementar memória estruturada em agentes Claude via padrão IANA-registrado

Veredito

Ferramenta robusta e bem-mantida com suporte oficial Anthropic (MCP Registry #2759). Ideal para quem precisa de contexto persistente estruturado em projetos Claude, mas requer familiaridade com o ecossistema FAF para aproveitar todo o potencial.

README

A tradução para o português deste README ainda está na fila.

claude-faf-mcp v5.6

FAF Trophy 100% IANA: vnd.faf+yamlIANA: vnd.fafm+yaml DOI: Context paperDOI: Memory paper

Home: faf.one/mcp Live demo: claude-faf-mcp.vercel.app

Persistent Project Context for Claude. 30 seconds. 🐘 Nelly Never Forgets.

FAF Anthropic MCP CI npm version NPM Downloads License: MIT Chat to FAFA live

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.

🏆 v5.6.1 — FAF-binary scoring has landed. faf_score now reads faf-cli's real scorer directly. Same number your AI and faf score (CLI) see. Truthful, IANA-spec, deterministic.

33 MCP tools. IANA-registered formats (application/vnd.faf+yaml · application/vnd.fafm+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:

WHO is it for?WHAT does it do?WHY build it?
UberPeople who need a rideTap a button, car arrivesTaxis were broken
AirbnbTravelers who can't afford hotelsStay in someone's spare roomMillions of empty rooms exist
SlackTeams drowning in emailOrganized group messagingDecisions buried in threads
VenmoFriends splitting billsSend money instantlySomeone 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 — 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

faf-cli — universal (any AI)

npx faf-cli auto

Same .faf, every surface — Claude, Gemini, Grok, Cursor. faf-cli on npm →

Claude Desktop — click, copy, paste, install

Click — one-click .mcpb

⬇ Download claude-faf-mcp-5.5.2.mcpb

Double-click. No terminal. No JSON config. 33 tools live in 10 seconds.

Copy — paste-prompt 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": "bunx", "args": ["claude-faf-mcp"]}}} and restart Claude Desktop.

Paste — claude_desktop_config.json

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

Install — manual npm

npm install -g 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

TierScoreWhat it means
🏆 TROPHY100%Gold Code — AI is optimized
★ GOLD99%+Near-perfect context
◆ SILVER95%+Excellent
◇ BRONZE85%+Production ready
● GREEN70%+Solid foundation
● YELLOW55%+AI flipping coins
○ RED<55%AI working blind
♡ WHITE0%No context at all

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


33 MCP Tools

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

Create & Detect

ToolPurpose
faf_initInitialize project DNA
faf_autoAuto-detect stack and populate context
faf_quickLightning-fast creation (3ms)
faf_readmeExtract context from README (+25-35% boost)
faf_formatsDiscover all formats in your project
faf_gitExtract context from any GitHub repo URL
faf_human_addAdd human context (the 6Ws)

Validate & Score

ToolPurpose
faf_scoreAI-readiness score (0-100%) with breakdown
faf_checkValidate .faf structure
faf_doctorDiagnose and fix common issues
faf_goGuided interview to Gold Code

Sync & Persist

ToolPurpose
faf_syncSync .faf → CLAUDE.md
faf_bi_syncBi-directional .faf ↔ CLAUDE.md
faf_tri_syncTri-sync .faf ↔ CLAUDE.md ↔ MEMORY.md — Pro feature, free for developers 🐘
faf_enhanceIntelligent enhancement

Export & Interop

ToolPurpose
faf_agentsImport/export AGENTS.md (OpenAI Codex)
faf_cursorImport/export .cursorrules (Cursor IDE)
faf_geminiImport/export GEMINI.md (Google Gemini)
faf_conductorImport/export Conductor directory

Read & Write

ToolPurpose
faf_readRead any file
faf_writeWrite any file
faf_statusProject status overview
faf_debugEnvironment inspection
faf_aboutWhat is .faf?

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

PackagePlatformRegistry
claude-faf-mcp (this)Claudenpm
faf-cliUniversal CLInpm + Homebrew
gemini-faf-mcpGoogle GeminiPyPI
grok-faf-mcpxAI Groknpm
rust-faf-mcpRustcrates.io
faf-wasmBrowser/Edgenpm
Chrome ExtensionBrowserChrome Web Store

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.


Citation

If you use claude-faf-mcp or the .faf / .fafm formats in research or production, please cite the format papers:

Wolfe, J. (2025). Format-Driven AI Context Architecture: The .faf Standard for Persistent Project Understanding. Zenodo. https://doi.org/10.5281/zenodo.18251362

Wolfe, J. (2026). Permanent Memory and Instant Recall: The .fafm Standard for Multi-Profile AI Agent Memory. Zenodo. https://doi.org/10.5281/zenodo.20348942

BibTeX

@article{wolfe2025faf,
  title     = {Format-Driven AI Context Architecture: The .faf Standard for Persistent Project Understanding},
  author    = {Wolfe, James},
  year      = {2025},
  month     = {nov},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.18251362},
  url       = {https://doi.org/10.5281/zenodo.18251362}
}

@article{wolfe2026fafm,
  title     = {Permanent Memory and Instant Recall: The .fafm Standard for Multi-Profile AI Agent Memory},
  author    = {Wolfe, James},
  year      = {2026},
  month     = {may},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.20348942},
  url       = {https://doi.org/10.5281/zenodo.20348942}
}

License

MIT — Free and open source


FAF Family

faf-clinpx faf-cli init — create .faf for any project
claude-faf-mcpMCP server for Claude Desktop
gemini-faf-mcpMCP server for Gemini CLI
grok-faf-mcpMCP server for Grok
faf-mcpMCP server for Cursor, Windsurf, Cline, VS Code
rust-faf-mcpMCP server in Rust
faf-skills17 Claude Code skills
faf.oneBlog, downloads, docs
IANA: vnd.faf+yamlContext format (2025-10-30)
IANA: vnd.fafm+yamlMemory format (2026-05-13)

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 · 2 IANA registrations: vnd.faf+yaml (Context) · vnd.fafm+yaml (Memory) · faf.one · npm

Ver o original no GitHub

Bom para

Relacionados