Complete AI Training

MCP server · Developer tools

.FAF Context MCP server

by Wolfe-Jam

Keeps one project context file and writes your AI tool's context files from it, with a readiness score.

Flow diagram: you ask your AI “Score my project context”, on your own computer the .FAF Context MCP server works with your project folder, and you get back A score and what to fix.

This is a helper that keeps one small file in your project called project.faf, and from that single file it writes the context files your AI tools expect. If your team uses different AI coding tools, each one wants its own file, and this server keeps them all saying the same thing. It is handy if you use Cursor, Windsurf, Cline or VS Code and you are tired of repeating the same project background to your AI.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to something outside the chat. This one connects your AI to a project context file in your repo, so the AI can read it, score it, and write the context files other tools need. You install it once, then just ask your AI in normal words.

What this MCP server does

You ask your AI something like score my project context or sync my context files. The AI passes that request to this helper, which runs on your own computer. The helper reads your project.faf file, checks it against a fixed list of 33 slots, and gives a score from 0 to 100 percent. It can also write files like CLAUDE.md, AGENTS.md, .cursorrules and GEMINI.md from that one source, so every tool sees the same picture. You get the score, a list of what is missing, or the updated files back in the chat.

Flow diagram: you ask your AI “Score my project context”, on your own computer the .FAF Context MCP server works with your project folder, and you get back A score and what to fix. Click to zoom

What you can do with it

  • Create a project.faf file for your project
  • Score your project context and see a readiness tier
  • Write CLAUDE.md, AGENTS.md, .cursorrules and GEMINI.md from one file
  • Import an existing context file back into project.faf
  • Diagnose why your score is low and get a fix for each gap
  • Build a project.faf from a public GitHub repo link
  • Check whether your human context fields are empty, generic or good

Try asking your AI

  • “Use FAF to initialize my project”
  • “Use FAF to score my AI-readiness”
  • “Use FAF to sync my context files”
  • “Use FAF to write all four context formats from project.faf”

What it gives back to you

You get answers in the chat: a score out of 100 with a tier name, a list of missing or weak slots, and short notes on how to fix them. When it writes files, it tells you which files it created or updated. Some tools show a preview first and only change things when you confirm.

Before you start

What you need

  • Node.js 22 or newer
  • An MCP client such as Cursor, Windsurf, Cline or VS Code (Claude Desktop users should use the claude-faf-mcp package instead)
  • A project folder you want to add context to

Good to know

It can write and replace context files in your project, so check the preview before you confirm, and it can read and write files in the folders it is allowed to reach.

Install it with your AI

Add .FAF Context MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check .FAF Context MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Developers and teams who use several AI coding tools and want one shared project context file instead of many.