What can you do with this server?

The grok-faf-mcp server is a zero-config MCP solution for Grok/xAI that manages .faf (AI context) files, enabling persistent, AI-readable project context across sessions. It offers 21 core tools across these areas: Project Context Management * faf_init — Create/initialize a project.faf file (captures stack, goals, architecture) * faf_status — Check if a project has a project.faf * faf_trust — Validate integrity of an existing project.faf * faf_chat — Guided interview to interactively build a project.faf Scoring & Analysis * faf_score — Calculate an AI-readiness score (0–100%) with breakdown and improvement suggestions Sync & Enhancement * faf_sync / faf_bi_sync — Bi-directional sync between project.faf and platform context files (CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md) * faf_enhance — AI-optimize .faf content with support for focus areas, target models, and consensus modes File System Operations * faf_read / faf_write — Read/write any file on the local filesystem * faf_list — Discover and list projects containing project.faf files RAG (Retrieval-Augmented Generation) * rag_query — Ask questions with RAG-enhanced context from xAI Collections, with LAZY-RAG caching for 100,000x speedup on repeated queries * rag_cache_stats / rag_cache_clear — Monitor and manage the RAG cache Utilities & Debugging * faf_about / faf_what / faf_guide — Learn about the .faf format and usage patterns * faf_debug — Inspect the MCP environment (working directory, permissions, CLI status) * faf_clear — Clear caches, temp files, and reset FAF state Deployment options include a hosted endpoint, self-deploy on Vercel, or run locally via npx. The server uses a Mk4 WASM scoring engine for fast execution (~0.5ms average).

Which integrations are available for this server?

Utilizes the IANA-registered .faf (YAML) format to manage project metadata, providing tools to initialize, auto-detect, and score project context for AI-readiness.

grok-faf-mcp

by Wolfe-Jam

Overview Schema Related Servers Score Discussions

TypeScript

Hybrid

grok-faf-mcp | FAST⚡️AF

Deploy with Vercel

NPM Downloads npm version License: MIT Vercel project.faf

📋 The 6 Ws - Quick Reference

Every README should answer these questions. Here's ours:

Question	Answer
👥 WHO is this for?	Grok/xAI developers and teams building with URL-based MCP
📦 WHAT is it?	First MCP server built for Grok - URL-based AI context via IANA-registered .faf format
🌍 WHERE does it work?	Vercel (production) • Local dev • Any MCP client supporting HTTP-SSE
🎯 WHY do you need it?	Zero-config MCP on a URL - Grok asked for it, we built it first
⏰ WHEN should you use it?	Grok integration testing, xAI projects, URL-based MCP deployments
🚀 HOW does it work?	Point to `https://grok-faf-mcp.vercel.app/sse` - 21 tools instantly available

For AI: Read the detailed sections below for full context. For humans: Use this pattern in YOUR README. Answer these 6 questions clearly.

The Problem

Every Grok session starts from zero. You re-explain your stack, your goals, your architecture. Every time.

.faf fixes that. One file, your project DNA, persistent across every session.

Without .faf  →  "I'm building a REST API in Rust with Axum and PostgreSQL..."
With .faf     →  Grok already knows. Every session. Forever.

One Command, Done Forever

faf_auto detects your project, creates a .faf, and scores it — in one shot:

faf_auto
━━━━━━━━━━━━━━━━━
Score: 0% → 85% (+85) 🥉 Bronze
Steps:
  1. Created project.faf
  2. Detected stack from package.json
  3. Synced CLAUDE.md

Path: /home/user/my-project

What it produces:

# project.faf — your project, machine-readable
faf_version: "3.3"
project:
  name: my-api
  goal: REST API for user management
  main_language: TypeScript
stack:
  backend: Express
  database: PostgreSQL
  testing: Jest
  runtime: Node.js
human_context:
  who: Backend developers
  what: User CRUD with auth
  why: Replace legacy PHP service

Every AI agent reads this once and knows exactly what you're building.

⚡ What You Get

URL:     https://grok-faf-mcp.vercel.app/
Format:  IANA-registered .faf (application/vnd.faf+yaml)
Tools:   21 core MCP tools (55 total with advanced)
Engine:  Mk4 WASM scoring (faf-scoring-kernel)
Speed:   0.5ms average (was 19ms — 3,800% faster with Mk4)
Tests:   179 passing (7 suites)
Status:  FAST⚡️AF

MCP over HTTP-SSE. Point your Grok integration at the URL. That's it.

Scoring: From Blind to Optimized

Tier	Score	What it means
🏆 Trophy	100%	Gold Code — AI is optimized
🥇 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

At 55%, Grok guesses half the time. At 100%, Grok knows your project.

🚀 Three Ways to Deploy

1. Hosted (Instant)

https://grok-faf-mcp.vercel.app/sse

Point your MCP client to this endpoint. All 21 tools available instantly.

2. Self-Deploy (Your Own Vercel)

Click the Deploy with Vercel button above. Zero config — get your own instance in 30 seconds.

3. Local (npx)

npx grok-faf-mcp

Or add to your MCP config:

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

🛠️ MCP Tools (21 Core)

Create & Detect

Tool	Purpose
`faf_init`	Create project.faf from your project
`faf_auto`	Auto-detect stack and populate context
`faf_score`	AI-readiness score (0-100%) with breakdown
`faf_status`	Check current AI-readability
`faf_enhance`	Intelligent enhancement

Sync & Persist

Tool	Purpose
`faf_sync`	Sync .faf → CLAUDE.md
`faf_bi_sync`	Bi-directional .faf ↔ platform context
`faf_trust`	Validate .faf integrity

Read & Write

Tool	Purpose
`faf_read`	Read any file
`faf_write`	Write any file
`faf_list`	Discover projects with .faf files

RAG & Grok-Exclusive

Tool	Purpose
`rag_query`	RAG-powered context retrieval
`rag_cache_stats`	RAG cache statistics
`rag_cache_clear`	Clear RAG cache
`grok_go_fast_af`	Auto-load .faf context for Grok

Plus 34 advanced tools available with FAF_SHOW_ADVANCED=true.

Performance

Execution:    0.5ms average (97% faster than v1.1)
Fastest:      3,360ns (version — nanosecond territory)
Slowest:      1.3ms (score — Mk4 WASM)
Improvement:  19ms → 0.5ms (3,800% faster)
Engine:       Mk4 WASM via faf-scoring-kernel
Memory:       Zero leaks
Transport:    HTTP-SSE (Vercel Edge)

Benchmarked 10x per tool, warmed up, on local execution.

Architecture

grok-faf-mcp v1.2.1
├── api/index.ts              → Vercel serverless (Express + SSE transport)
├── src/
│   ├── server.ts             → MCP server (ClaudeFafMcpServer)
│   ├── handlers/
│   │   ├── championship-tools.ts  → 55 tool definitions
│   │   ├── tool-registry.ts       → Visibility filtering (core/advanced)
│   │   └── engine-adapter.ts      → FAF engine bridge
│   └── faf-core/
│       └── compiler/
│           └── faf-compiler.ts    → Mk4 WASM scoring + Mk3.1 fallback
├── smithery.yaml             → Smithery listing config
└── vercel.json               → Vercel routing

Scoring pipeline: TypeScript compiler parses .faf → detects project type → The Bouncer injects slotignored for inapplicable slots → faf-scoring-kernel (WASM) scores → falls back to Mk3.1 if kernel unavailable.

Testing

179 tests across 7 suites:

npm test    # runs all 179

Suite	Tests	Coverage
Desktop-native validation	10	Core native functions, security, performance
MCP protocol	28	Tool registration, transport, error handling
Compiler scoring	22	Mk4 engine, type detection, slot counting
RAG system	19	Query, caching, context retrieval
Engine adapter	35	CLI detection, fallback behavior
Integration	40	End-to-end tool execution
WJTTC certification	25	Championship-grade compliance

🔗 Endpoints

Endpoint	URL
Root	`https://grok-faf-mcp.vercel.app/`
SSE	`https://grok-faf-mcp.vercel.app/sse`
Health	`https://grok-faf-mcp.vercel.app/health`
Info	`https://grok-faf-mcp.vercel.app/info`

📦 Ecosystem

One format, every AI platform.

Package	Platform	Registry
grok-faf-mcp (this)	xAI Grok	npm
claude-faf-mcp	Anthropic	npm + MCP #2759
gemini-faf-mcp	Google	PyPI
rust-faf-mcp	Rust	crates.io
faf-mcp	Universal (Cursor, Windsurf, Cline)	npm
faf-cli	Terminal CLI	npm + Homebrew

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

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

📄 License

MIT — Free and open source

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

Install Server

security – no known vulnerabilities

license - permissive license

quality - not tested

How are these scores calculated?

Resources

Need Help?

Related Servers

Tools

View all tools

Latest Blog Posts

Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security
Open Source Has a Bot Problem
By punkpeye on March 19, 2026.
open source

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Wolfe-Jam/grok-faf-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server