Claude FAF

Provides an MCP server for the .FAF AI context format enabling persistent project context and 50+ tools.

typescript

8

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "wolfe-jam-claude-faf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "claude-faf-mcp"
      ]
    }
  }
}

You set up and run an MCP server that provides a persistent AI context for your project using the .FAF format. This server lets Claude Desktop (and other MCP clients) access a structured, universal context so your AI can understand your project’s DNA, tools, and workflows without repeated setup. By running the FAF MCP server, you enable fast, consistent context delivery and a scalable base for AI-assisted development.

How to use

You connect to the FAF MCP server from your MCP client by configuring a local or remote server entry. Use the provided stdio configuration to run the server locally, then point your client at the local MCP entry or at a remote endpoint if you host it elsewhere. Once connected, your client can leverage the FAF context and the built-in tools to analyze, enhance, and score your project context.

How to install

Prerequisites you need before installation are Node.js and npm. Ensure Node.js is installed on your system.

Install the FAF MCP server globally with npm.

Then configure your Claude Desktop client to load the FAF MCP server using the provided MCP configuration snippet and restart Claude Desktop.

Additional notes

MCP connection method shown here is a local stdio setup. The exact command to run the FAF MCP server is the npx invocation described in the usage snippet. If you prefer to manage the server as a separate process, you can rely on the same command to start it in a shell or script.

You can also keep a ready-made configuration handy for instant setup across machines by using the exact JSON below in your claude_desktop_config.json under the mcpServers section.

Example quick start

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

Available tools

faf_quick

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

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

faf_compress

Intelligent size optimization