by wolfe-jam
FAF offers free file synchronization software with project context management, automated scoring, health checks, and mul
Maintains persistent project context for AI assistants by automatically analyzing your codebase and syncing documentation to prevent context drift.
You can install FAF (File & Project Context) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
FAF (File & Project Context) is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
FAF (File & Project Context) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
FAF (File & Project Context) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
FAF (File & Project Context) reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
FAF (File & Project Context) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We evaluated FAF (File & Project Context) against two servers with overlapping tools; this profile had the clearer scope statement.
Useful MCP listing: FAF (File & Project Context) is the kind of server we cite when onboarding engineers to host + tool permissions.
We wired FAF (File & Project Context) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Useful MCP listing: FAF (File & Project Context) is the kind of server we cite when onboarding engineers to host + tool permissions.
FAF (File & Project Context) reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
FAF (File & Project Context) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
showing 1-10 of 48
IANA-Registered Format for AI Context · application/vnd.faf+yaml
3Ws · Quick Start · Website · DAAFT Analysis · npm · Tools · Tiers · CLI Companion · Changelog
--- ## 💡 The 3Ws — Start Here
Answer 3 questions. That's all your AI needs to start.
| Question | What to answer |
|----------|---------------|
| **👥 WHO** is it for? | The people who will use this. Not you — them. |
| **📦 WHAT** does it do for them? | The value they get. Not features — the outcome. |
| **🎯 WHY** should it exist? | What's broken today? Why does this need to exist? |
**That's it.** Tell Claude your 3Ws and FAF turns them into project DNA that never drifts.
**[Build yours → faf.one/ideas](https://faf.one/ideas)**
---
## 📋 The 6 Ws — Quick Reference
| Question | Answer |
|----------|--------|
| **👥 WHO** is this for? | Claude Desktop & Claude Code users, MCP server operators, any MCP client |
| **📦 WHAT** is it? | 33-tool MCP server for AI context — IANA-registered format (`application/vnd.faf+yaml`) |
| **🌍 WHERE** does it work? | Claude Desktop, Claude Code, any MCP-compatible client |
| **🎯 WHY** do you need it? | 91% token waste eliminated, zero context-drift — saves $5,460/year per developer |
| **⏰ WHEN** should you use it? | New projects (day one), existing projects (now), exploring repos (instantly) |
| **🚀 HOW** does it work? | `npx claude-faf-mcp` — one line in your MCP config |
**For AI:** Read the detailed sections below for full context.
**For humans:** Use this pattern in YOUR README. **[Build yours →](https://faf.one/6ws)**
---
## Not a Developer?
No problem. FAF works for anyone using Claude Desktop.
**3 steps:**
1. Install FAF from Claude Desktop → Settings → Extensions
2. Tell Claude your 3Ws: *"I'm building [what] for [who] because [why]"*
3. Claude creates your project DNA — context that never drifts
No terminal. No code. Just answer 3 questions.
**Try it:** Tell Claude *"Score my project's AI-readiness and tell me how to improve"* — it works on any project, any language, any framework.
---
## The Problem: Context-Drift
AI assistants forget. They misunderstand. They drift.
Every new session, every new file, every new developer — AI starts guessing again. Your codebase context leaks away. Yesterday's perfect assistant becomes today's confused intern.
**The cost:** 91% of tokens wasted on rediscovery. $5,460/year per developer. At 50 devs, that's $273k–$507k annually — before counting project failures from compounding context loss. **[Full DAAFT analysis →](https://faf.one/daaft)**
**.FAF fixes this permanently.**
---
## The Solution: Gold Code
```
🏆 FAF AI-READINESS: 100/100 — GOLD CODE
├─ Project DNA locked in ├─ Zero context-drift
├─ Architecture understood ├─ Eternal bi-sync active
└─ Every session starts smart └─ AI works WITH you
```
**Gold Code = AI Optimized.** Your project DNA lives in `project.faf`. AI reads it instantly. Context never drifts.
---
## 🔄 Eternal Bi-Sync (Free Forever)
The magic: `.faf` ↔ `CLAUDE.md` stay synchronized in milliseconds.
```
project.faf ←──── 8ms ────→ CLAUDE.md
│ │
└── Single source of truth ──┘
```
- Update either file → both stay aligned
- Zero manual maintenance
- Works across teams, branches, sessions
- **Context never goes stale**
### 🐘 Tri-Sync: Add RAM (Pro)
bi-sync is core. tri-sync adds more — your AI remembers across sessions.
```
bi-sync = ROM (.faf) ↔ CLAUDE.md ← free forever
tri-sync = ROM ↔ CLAUDE.md ↔ RAM (MEMORY.md) ← Pro
```
**Feed Nelly 🐘 — she never forgets.** A dime a day ($3/mo) · a nickel a day ($19/yr) · $29/yr Global (CLI + MCP). 14-day free trial, no signup.
**[Friends of FAF → faf.one/pro](https://faf.one/pro)**
---
## Tier System: From Blind to Optimized
| Tier | Score | Status |
|------|-------|--------|
| 🏆 **Trophy** | 100% | **AI Optimized** — Gold Code |
| 🥇 **Gold** | 99%+ | Near-perfect context |
| 🥈 **Silver** | 95%+ | Excellent |
| 🥉 **Bronze** | 85%+ | Production ready |
| 🟢 **Green** | 70%+ | Solid foundation |
| 🟡 **Yellow** | 55%+ | AI flipping coins |
| 🔴 **Red** | <55% | AI working blind |
| 🤍 **White** | 0% | No context at all |
**At 55%, AI is guessing half the time.** At 100%, AI is optimized.
---
## 💎 Lifecycle Value
Setup savings get you started. Lifecycle optimization keeps you ahead.
| When | Without FAF | With FAF |
|------|-------------|----------|
| **Day 1** | 20 min setup per dev | 0 min — instant context |
| **Month 1** | AI forgets between sessions | AI remembers everything |
| **Year 1** | New devs re-explain everything | New devs inherit full context |
| **Year 3+** | Institutional knowledge lost | Project DNA preserved forever |
**Setup savings: 20 minutes. Lifecycle savings: Infinite.**
---
## ⚡ 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)](https://github.com/Wolfe-Jam/claude-faf-mcp/releases/latest)
---
## 🛠️ 33 MCP Tools
All tools run standalone — zero CLI dependencies, 16.2x faster than process spawning.
| Tool | Purpose |
|------|---------|
| `faf_init` | Initialize project DNA |
| `faf_score` | Check AI-readiness (0-100%) |
| `faf_sync` | Bi-sync .faf ↔ CLAUDE.md |
| `faf_tri_sync` | Tri-sync .faf → MEMORY.md *(Pro — 14-day free trial)* |
| `faf_auto` | Auto-detect and populate context |
| `faf_enhance` | Intelligent enhancement |
| `faf_quick` | Lightning-fast creation (3ms) |
| `faf_readme` | Extract 6 Ws from README (+25-35% boost) |
| `faf_human_add` | Add human context (Claude Code compatible) |
| `faf_agents` | Import/export/sync AGENTS.md (OpenAI Codex) |
| `faf_cursor` | Import/export/sync .cursorrules (Cursor IDE) |
| `faf_gemini` | Import/export/sync GEMINI.md (Google Gemini) |
| `faf_git` | Extract context from any GitHub repo URL |
| `faf_conductor` | Import/export Conductor directory |
**Performance:** 19ms average execution. Fastest: 1ms.
### ✨ New in v4.5.0: AI Format Interop
Define once in `.faf`, generate all four AI instruction formats:
```
project.faf → CLAUDE.md (Anthropic)
→ AGENTS.md (OpenAI / Linux Foundation)
→ .cursorrules (Cursor IDE)
→ GEMINI.md (Google Gemini CLI)
```
**Bi-sync all at once:**
```
faf_bi_sync { all: true }
```
**GitHub context extraction:**
```
faf_git { url: "https://github.com/owner/repo" }
→ Generates .faf from any public GitHub repo
```
### 6Ws Builder
Answer 6 questions (WHO/WHAT/WHERE/WHY/WHEN/HOW) to boost AI-readiness by +25-35%. Two ways:
- **Web:** [faf.one/6ws](https://faf.one/6ws) — Fill form, copy YAML, paste into Claude with `faf_human_add`
- **CLI:** `faf 6ws` — Interactive terminal workflow
### README Auto-Extract
Already have a README? Extract context automatically:
```javascript
faf_readme // Preview extracted context
faf_readme { merge: true } // Merge into project.faf
faf_readme { merge: true, overwrite: true } // Overwrite existing fields
```
Same +25-35% score boost, zero manual work.
---
## 🎯 The .FAF Position
```
Model Context Protocol
───── ─────── ────────
Claude → .faf → MCP
Gemini → .faf → MCP
Codex → .faf → MCP
Any LLM → .faf → MCP
```
**.FAF is the foundational layer.** Universal context format. IANA-registered (`application/vnd.faf+yaml`). Works with any AI.
---
## 📦 Ecosystem
- **[faf-cli](ht
---Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.
