Skip to main content
Glama

Official MCP server for .FAF (Foundational AI-context Format) with 52 tools - Persistent project context that integrates seamlessly with Claude Desktop workflows

NPM Downloads Discord Chrome Web Store Website License: MIT


โŒ Without FAF

You: "Update the auth module" AI: "What framework? What patterns? Where are the files?" You: "It's Express with JWT, files in /src/auth..." AI: "What's the error handling approach?" You: "We use custom AppError class..." AI: "Database schema?" You: [15 minutes later, still explaining]

Every session. Every project. Every AI tool. Starting over.

โœ… With FAF

You: "Update the auth module" AI: [Reads project.faf] "Got it. Express + JWT, AppError pattern, files in /src/auth, PostgreSQL with Prisma. Making the change."

One file. Persistent context. Every AI knows your project.


๐Ÿ AI-Readiness Scorecard

The closer you get to 100% the better AI can assist you.

At 55% you are building your project with half a blueprint and basically flipping a coin with AI. .FAF defines, and AI becomes optimized for Context with the project.faf file.

โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ” ๐Ÿ† FAF AI-READINESS SCORE: 100/100 โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ” ๐Ÿ“Š CORE INTELLIGENCE ๐ŸŽฏ CONTEXT DELIVERY โ”œโ”€ Project DNA [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ MCP Protocol [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ Architecture Map [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ 52 Native Tools [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ Domain Model [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ IANA Format [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ””โ”€ Version Tracking [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ””โ”€ Universal Context [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% ๐Ÿš€ PERFORMANCE โšก STANDALONE OPERATION โ”œโ”€ 16.2x Speedup [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ Zero Dependencies [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ 19ms Avg Execution [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ Bundled Engine [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ 52/52 Tools Active [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ”œโ”€ Direct Function [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ””โ”€ Zero Memory Leaks [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% โ””โ”€ 14 Bundled Cmds [โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ] 100% ๐Ÿ† Status: Trophy - Perfect AI context โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”โ”

Tier System

Tier

Score

Emoji

Meaning

Trophy

100%

๐Ÿ†

Perfect AI context

Gold

99%+

๐Ÿฅ‡

Exceptional

Silver

95%+

๐Ÿฅˆ

Top tier - Excellent

Bronze

85%+

๐Ÿฅ‰

Strong - Production ready

Green

70%+

๐ŸŸข

Good - Solid foundation

Yellow

55%+

๐ŸŸก

Caution - Needs improvement

Red

<55%

๐Ÿ”ด

Critical - AI working blind

White

0%

๐Ÿค

Empty - No context


โšก Quick Start

Copy and paste this to Claude/your AI:

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.

One-Click Alternative: Desktop Extension (.mcpb)


๐ŸŽฏ What is FAF?

The .FAF Position in the MCP Ecosystem:

Model Context Protocol โ”€โ”€โ”€โ”€โ”€ โ”€โ”€โ”€โ”€โ”€โ”€โ”€ โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€ LLM โ†’ IANA Format โ†’ Open Protocol Claude โ†’ .faf โ†’ MCP Gemini โ†’ .faf โ†’ MCP Codex โ†’ .faf โ†’ MCP

.FAF is the foundational, universal base layer for any Model using the MCP Protocol. It provides the standardized Context that makes the Model Context Protocol work for everyone.


๐Ÿ› ๏ธ Core Features

52 MCP Tools (100% Standalone)

  • faf_quick - Lightning-fast project.faf creation (3ms avg)

  • faf_readme - Smart 6 Ws extraction from README.md (+25-35% score boost)

  • faf_human_add - Non-interactive human context entry (Claude Code compatible)

  • faf_enhance - Intelligent enhancement with auto-detection

  • faf_read - Parse and validate FAF files

  • faf_write - Create/update FAF with validation

  • faf_score - AI-readiness scoring engine (with subsite auto-detection)

  • faf_compress - Intelligent size optimization

  • 14 bundled commands - Zero CLI dependencies, 16.2x faster

IANA-Registered Standard

  • Official MIME type: application/vnd.faf+yaml

  • W3C-compliant structured format

  • Universal AI context protocol

  • Cross-platform compatibility

Performance

  • 16.2x faster than CLI versions (direct function calls vs process spawning)

  • 19ms average execution across all bundled commands

  • Fastest: 1ms (formats command)

  • Zero memory leaks


๐Ÿ“š Documentation


๐Ÿ† Why FAF?

"README for the AI era" โ€” Gemini CLI

Persistent Context - Your project's DNA lives in project.faf, readable by any AI or human

Universal Format - IANA-registered standard works across Claude, Gemini, Codex, any LLM

Zero Setup Tax - One file (project.faf) eliminates AI context setup across your entire team

Quality Engineering - Strict TypeScript, zero runtime errors


๐Ÿ“ฆ Ecosystem


๐Ÿ“„ License

MIT License - Free and open source


Built for speed and reliability โšก

"It's so logical if it didn't exist, AI would have built it itself" โ€” Claude

-
security - not tested
A
license - permissive license
-
quality - not tested

Latest Blog Posts

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/claude-faf-mcp'

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