data-ai MCP Server
Persistent Project Context for Claude — IANA-registered .faf format · Core 14 MCP tools (30 with FAF_TOOLS=all) + 2 prompts · MCP Registry #2759
Discovered via unknown and last synced 1w ago.
1. Install the package
npx -y claude-faf-mcp
2. Add to claude_desktop_config.json
{
"mcpServers": {
"claude-faf-mcp": {
"command": "npx",
"args": [
"-y",
"claude-faf-mcp"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
What the .faf format is
Read the 6Ws from README.md; `apply` fills only empty slots
Write GEMINI.md (Google Gemini CLI)
Platform
Score
Set one 6W slot in project.faf
Bi-directional .faf ↔ CLAUDE.md
crates.io
Create project.faf for a folder (faf-cli detects the stack)
AI-readiness score (0-100%), from faf-cli
Intelligent enhancement
Create project.faf from one line: name, goal, language, framework, hosting
Diagnose project.faf: each finding with the tool that fixes it
Write AGENTS.md (OpenAI Codex and other agents)
The active project, write access and the bundled faf-cli version
The goal and the 6Ws, by question and answer
Write .cursorrules (Cursor IDE)
Fill project.faf from the repo's own files, then CLAUDE.md
faf-cli's validateFaf and the state of every slot
Purpose
Whether the project has a .faf, with its first lines
mcp-server
Author a project.faf from a repo URL (clones it with git — uses the network)
Write CLAUDE.md from project.faf — `agents`/`cursor`/`gemini`/`copilot`/`all` also write AGENTS.md / .cursorrules / GEMINI.md / copilot-instructions.md
Write Google Conductor's conductor/ files
npm
Write faf's block into the MEMORY.md Claude Code loads for this project 🐘
Read a file inside the active project
Chrome Web Store
Write any file
Benchmark AI grounding — cold vs with the .faf, graded mechanically, with a receipt
Validate project.faf and return a trust receipt for its score
Install the SessionStart hook in the project settings (preview first)
Show or set the active project; `detail` returns the .faf text
Remember a decision across sessions (the project soul, soul.fafm)
Recall memories from the project soul
Start here: the project, its score and the steps to 100% (reads only)
The formats faf-cli finds in the folder, and what faf_auto would write (dry run)
The project's .faf-dna lineage (reads only)
List a folder inside the active project
npm + Homebrew