claude-faf
📇 🏠 - First & only persistent project context MCP. Provides .faf (Foundational AI-context Format) Project DNA with 33+ tools, Podium scoring (0-100%), and format-driven architecture. Official Anthropic Registry. 10k+ npm downloads.
What is claude-faf?
claude-faf is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 📇 🏠 - first & only persistent project context mcp. provides .faf (foundational ai-context format) project dna with 33+ tools, podium scoring (0-100%), and format-driven architecture. official anthro...
📇 🏠 - First & only persistent project context MCP. Provides .faf (Foundational AI-context Format) Project DNA with 33+ tools, Podium scoring (0-100%), and format-driven architecture. Official Anthropic Registry. 10k+ npm downloads.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 📇 🏠 - First & only persistent project context MCP. Provides
Use Cases
Maintainer
Works with
Installation
NPM
npx -y claude-faf-mcpManual Installation
npx -y claude-faf-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use claude-faf
claude-faf-mcp is the first and only MCP server designed to provide persistent project context to Claude and other AI assistants through the .faf (Foundational AI-context Format) standard. It creates and maintains a project.faf file in your repository that captures the essential project definition — what you're building, for whom, and why — and makes it available across every session so Claude never loses context when you start a new conversation. With 32 tools for creating, scoring, syncing, and exporting project context, it also includes a Podium scoring system (0–100%) to measure and improve your project's AI readiness.
Prerequisites
- Node.js 18 or later (for npx/bunx execution)
- Claude Desktop or another MCP-compatible client
- A project directory where you want persistent AI context stored
- No external API keys required — everything runs locally
Install via npm (global)
Install the claude-faf-mcp package globally so it is available as an npx command. Alternatively, use bunx if you have Bun installed.
npm install -g claude-faf-mcpAdd to Claude Desktop configuration
Open claude_desktop_config.json and add the faf server entry. The command uses bunx by default but npx works equally well.
{
"mcpServers": {
"faf": {
"command": "npx",
"args": ["-y", "claude-faf-mcp"]
}
}
}Restart Claude Desktop
Save the configuration file and restart Claude Desktop. The 32 faf tools will be registered and available in your next conversation.
Initialize project context
In a Claude conversation, navigate to your project directory and run /faf to auto-detect, score, and set up your project context. Alternatively, describe your project: 'I'm building [what] for [who] because [why]' and Claude will use faf_init to create a project.faf file.
Score your project's AI readiness
Use faf_score to get a Podium score from 0–100% measuring how well your project context is defined for AI consumption. Use faf_doctor to diagnose gaps and faf_enhance to improve the context.
Sync context across tools
Export your project context to other AI tools using the sync tools: faf_cursor for Cursor IDE context, faf_agents for agents.md format, faf_gemini for Gemini, and faf_conductor for multi-agent orchestration.
claude-faf Examples
Client configuration (Claude Desktop)
Add this block to claude_desktop_config.json to enable the claude-faf-mcp server. No environment variables or API keys are needed.
{
"mcpServers": {
"faf": {
"command": "npx",
"args": ["-y", "claude-faf-mcp"]
}
}
}Prompts to try
Sample prompts that exercise the core faf tools for project context management.
- "Run /faf to check and score my project context."
- "Initialize project context: I'm building a SaaS invoicing tool for freelancers because they waste hours on manual billing."
- "What is the current Podium score for this project and what's needed to reach 80%?"
- "Sync my project context to Cursor IDE format."
- "Export this project's faf context as an agents.md file for multi-agent use."Troubleshooting claude-faf
The /faf command is not recognized after installation
Ensure Claude Desktop was fully restarted after saving the config file. Verify the MCP server is registered by checking Settings > MCP Servers in Claude Desktop. If npx fails, try switching the command to bunx in the config.
project.faf file is created but context is not persisting between sessions
The project.faf file must be in the root of the project directory that Claude has access to. Use faf_status to confirm the file path is correct and faf_sync to explicitly push context into Claude's active session.
faf tools show as unavailable after Claude Desktop update
Run 'npm update -g claude-faf-mcp' to get the latest version, then restart Claude Desktop. Breaking changes between major versions may require re-running faf_init on existing project.faf files.
Frequently Asked Questions about claude-faf
What is claude-faf?
claude-faf is a Model Context Protocol (MCP) server that 📇 🏠 - first & only persistent project context mcp. provides .faf (foundational ai-context format) project dna with 33+ tools, podium scoring (0-100%), and format-driven architecture. official anthropic registry. 10k+ npm downloads. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install claude-faf?
Install via npm with the command: npx -y claude-faf-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with claude-faf?
claude-faf works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is claude-faf free to use?
Yes, claude-faf is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
claude-faf Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to claude-faf? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up claude-faf in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use claude-faf?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.