Gemini FAF MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
pip install gemini-faf-mcp
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add gemini-faf-mcp -- node "<FULL_PATH_TO_GEMINI_FAF_MCP>/dist/index.js"

Replace <FULL_PATH_TO_GEMINI_FAF_MCP>/dist/index.js with the actual folder you prepared in step 1.

README.md

Unify your AI project context with IANA-registered FAF files.

gemini-faf-mcp 🧬

Unify your AI project context. One file to rule them all. Bridges CLAUDE.md, GEMINI.md, and AGENTS.md into a single, IANA-registered source of truth.

Stop re-explaining your project to every new AI session.

Gemini, Claude, and OpenAI all have different ways of "learning" your project. FAF (Foundational AI-context Format) unifies them into one machine-readable .faf file.

Result: Zero context drift. Zero-minute onboarding. 100% project alignment.

Feature CLAUDE.md GEMINI.md AGENTS.md project.faf
Format Markdown Markdown Markdown Structured YAML
Schema Custom Custom Custom IANA Standard
Scoring No No No Yes (0-100%)
Auto-Detect No No No Yes (153+ files)
Vendor Neutral No No No Yes

🚀 One-Minute Setup

1. Install

pip install gemini-faf-mcp

2. Auto-Detect & Initialize

Scan your existing project and create your DNA in one command:

# Detects Python (FastAPI/Django), JS/TS (React/Next.js), Rust (Axum), and Go (Gin)
faf auto

3. Add to Gemini CLI

gemini extensions install https://github.com/Wolfe-Jam/gemini-faf-mcp

💎 The "One-File" Advantage

A .faf file is structured YAML that captures your project DNA. Every AI agent reads it once and knows exactly what you're building.

# project.faf — your project, machine-readable
faf_version: '2.5.0'
project:
  name: my-api
  goal: REST API for user management
  main_language: Python
stack:
  backend: FastAPI
  database: PostgreSQL
  testing: pytest
human_context:
  who: Backend developers
  what: User CRUD with auth
  why: Replace legacy PHP service

Result: Gemini reads this once and knows your project. No 20-minute onboarding. No wrong assumptions. Every session starts aligned.


Auto-Detect Your Stack

faf_auto scans your project's manifest files and generates a .faf with accurate slot values. No manual entry needed.

> Auto-detect my project stack
{
  "detected": {
    "main_language": "Python",
    "package_manager": "pip",
    "build_tool": "setuptools",
    "framework": "FastMCP",
    "api_type": "MCP",
    "database": "BigQuery"
  },
  "score": 100,
  "tier": "Trophy"
}

What it scans:

File Detects
pyproject.toml Python + build system + frameworks (FastAPI, Django, Flask, FastMCP) + databases
package.json JavaScript/TypeScript + frameworks (React, Vue, Next.js, Express)
Cargo.toml Rust + cargo + frameworks (Axum, Actix)
go.mod Go + go modules + frameworks (Gin, Echo)
requirements.txt Python (fallback)
Gemfile Ruby
composer.json PHP

Priority rule: pyproject.toml / Cargo.toml / go.mod take priority over package.json. Only sets values that are actually detected — no hardcoded defaults.


All 12 Tools

Create & Detect

Tool What it does
faf_init Create a starter .faf file with project name, goal, and language
faf_auto Auto-detect stack from manifest files and generate/update .faf
faf_discover Find .faf files in the project tree

Validate & Score

Tool What it does
faf_validate Full validation — score, tier, errors, warnings
faf_score Quick score check (0-100%) with tier name

Read & Transform

Tool What it does
faf_read Parse a .faf file into structured data
faf_stringify Convert parsed FAF data back to clean YAML
faf_context Get Gemini-optimized context (project + stack + score)

Export & Interop

Tool What it does
faf_gemini Export GEMINI.md with YAML frontmatter for Gemini CLI
faf_agents Export AGENTS.md for OpenAI Codex, Cursor, and other AI tools

Reference

Tool What it does
faf_about FAF format info — IANA registration, version, ecosystem
faf_model Get a 100% Trophy-scored example .faf for any of 15 project types

Score and Tier System

Your .faf file is scored on completeness — how many slots are

Tools (12)

faf_initCreate a starter .faf file with project name, goal, and language.
faf_autoAuto-detect stack from manifest files and generate/update .faf.
faf_discoverFind .faf files in the project tree.
faf_validateFull validation of the .faf file including score, tier, errors, and warnings.
faf_scoreQuick score check (0-100%) with tier name.
faf_readParse a .faf file into structured data.
faf_stringifyConvert parsed FAF data back to clean YAML.
faf_contextGet Gemini-optimized context including project, stack, and score.
faf_geminiExport GEMINI.md with YAML frontmatter for Gemini CLI.
faf_agentsExport AGENTS.md for OpenAI Codex, Cursor, and other AI tools.
faf_aboutGet FAF format info including IANA registration and version.
faf_modelGet a 100% Trophy-scored example .faf for any of 15 project types.

Configuration

claude_desktop_config.json
{"mcpServers": {"gemini-faf-mcp": {"command": "faf", "args": ["mcp"]}}}

Try it

Auto-detect my project stack and initialize a new .faf file.
Validate my current project .faf file and tell me how to improve my score.
Generate the GEMINI.md file for my current project context.
Export the AGENTS.md file so I can use this project context in Cursor.
Show me a 100% scored example .faf file for a Python FastAPI project.

Frequently Asked Questions

What are the key features of Gemini FAF MCP?

Unifies project context into a single IANA-registered .faf YAML file. Auto-detects project stacks from manifest files like pyproject.toml and package.json. Provides a scoring and tier system to ensure project context completeness. Bridges context across different AI platforms including Gemini, Claude, and OpenAI. Supports transformation of project context into platform-specific formats.

What can I use Gemini FAF MCP for?

Eliminating context drift across multiple AI sessions and platforms. Standardizing project documentation for AI agents to improve onboarding speed. Validating project configuration completeness before starting new development tasks. Syncing project DNA across different AI-powered IDEs and CLI tools.

How do I install Gemini FAF MCP?

Install Gemini FAF MCP by running: pip install gemini-faf-mcp

What MCP clients work with Gemini FAF MCP?

Gemini FAF MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Gemini FAF MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare