faf-mcp
faf-mcp is a Model Context Protocol server that manages persistent project context for AI assistants, using a single .faf file as the source of truth and syncing it across multiple AI platform formats (CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md, etc.).
Context Initialization & File Management
faf_init/faf_quick— Create a.faffile for a projectfaf_read/faf_write— Read and write files with path-safetyfaf_list— List directories and discover projects with.faffilesfaf_context— Set or view active project path for subsequent callsfaf_clear— Clear caches and reset FAF state
Sync & Interop
faf_sync— Sync.faftoCLAUDE.mdfaf_bi_sync— Bi-directional sync across ALL formats at once, with optional real-time watchingfaf_agents— Import/Export/SyncAGENTS.md(OpenAI/Codex)faf_cursor— Import/Export/Sync.cursorrules(Cursor IDE)faf_gemini— Import/Export/SyncGEMINI.md(Google Gemini)faf_conductor— Import/Export withconductor/directory (Google Conductor)
Project Health & Scoring
faf_score— Calculate AI-readiness score (0–100%) with detailed breakdownfaf_status— Check if a project has.fafand its AI-readability statusfaf_check— Quality inspection ofhuman_contextfieldsfaf_trust— Validate.fafintegrityfaf_doctor— Diagnose and fix common setup issues
Context Enhancement & Guided Setup
faf_enhance— Enhance.fafwith AI optimization (completeness, human context, AI instructions)faf_go— Guided interview to reach 100% scorefaf_auto— One-command setup: init + sync + formats + bi-sync + scorefaf_readme— Extract 6 Ws (Who/What/Why/Where/When/How) from README intohuman_contextfaf_human_add— Add or update individualhuman_contextfieldsfaf_formats— Discover all tech formats (154+ validated types) to fill stack slotsfaf_dna— View project DNA evolution journey
GitHub & Cloud
faf_git— Generate.faffrom any GitHub repository URL without cloningfaf_cloud_publish/faf_cloud_fetch/faf_cloud_list/faf_cloud_search/faf_cloud_share— Upload, fetch, list, search, and share project context via mcpaas.live
Utility & Meta
faf_about/faf_what— Learn about the.fafformatfaf_guide— Usage guide for MCP host patternsfaf_debug— Debug environment info (working directory, permissions, FAF CLI status)faf_friday— Fun FAF facts and fuzzy matching with typo tolerance
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@faf-mcpsync .faf to all AI formats"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Home: wolfe-jam.github.io/faf-mcp · Hosted MCP endpoint: https://ide.faf.one/mcp/v1 (Streamable HTTP)
The MCP you didn't realise you needed, or wanted but didn't know who to ask, is here. Building on 100,000+ downloads across the FAF ecosystem, we bring you faf-mcp to cure your syncing pain and fuel your chosen AI with optimized context, on-demand.
What's New in 2.3.0 — The Curated Edition
The tools you actually need, up front. faf-mcp now leads with 15 essential tools by default — a clean, focused surface instead of a wall of options. Need everything? Set FAF_TOOLS=all for the full 29 (every tool stays callable by name either way). And every Core tool's description was rewritten so your AI picks the right one, first time.
Related MCP server: gemini-faf-mcp
Define once. Sync everywhere.
You maintain .cursorrules. Your teammate uses AGENTS.md. Someone on the team just switched to Gemini. Every AI tool wants its own context file — and they all say the same thing in different formats.
faf-mcp is the dedicated MCP server for Cursor, Windsurf, Cline, VS Code, and every non-Claude platform. One .faf file in your repo, synced to every format your team needs.
project.faf
│
┌────────┬───────┴───────┬────────────┐
▼ ▼ ▼ ▼
CLAUDE.md AGENTS.md .cursorrules GEMINI.md
(Claude) (Codex) (Cursor) (Gemini)Quick Start
Cursor — one click:
Everywhere else:
bunx faf-mcpAdd to your MCP config:
{"mcpServers": {"faf": {"command": "bunx", "args": ["faf-mcp"]}}}Platform | Config File |
Cursor |
|
Windsurf |
|
Cline | Cline MCP settings |
VS Code | MCP extension config |
Claude Desktop | Use claude-faf-mcp |
Three Ways to Deploy
Door | Method | Best For |
Hosted | Zero-install, point any MCP client to the URL | |
Self-Deploy | Your own instance, full control | |
Local |
| IDE integration via stdio transport |
Hosted (mcpaas.live)
Point your MCP client to https://ide.faf.one/mcp/v1 — no install, no config, no maintenance. Served from 300+ Cloudflare edges with sub-ms cold starts via 2.7KB Zig-WASM engine.
Self-Deploy (Vercel)
Deploy your own MCP server on Vercel in one click. Once deployed, your server exposes:
/health— Health check/info— Server metadata + tool list/mcp/v1— MCP Streamable HTTP transport
Local (npm)
npx faf-mcpInterop Tools
Tool | Platform | Action |
| OpenAI Codex | Import/export/sync AGENTS.md |
| Cursor IDE | Import/export/sync .cursorrules |
| Google Gemini | Import/export/sync GEMINI.md |
| Conductor | Import/export directory structure |
| GitHub | Generate .faf from any repo URL |
# Sync to all formats at once
faf bi-sync --all
# Generate .faf from any GitHub repo
faf_git { url: "https://github.com/facebook/react" }Core tier: 15 essential tools shown by default; set FAF_TOOLS=all for the full 29 (every tool stays callable by name either way) · with CLI fallback · 9 test suites · 7 bundled parsers
Cloud Sync
Share your FAF context globally via mcpaas.live:
Tool | Purpose |
| Upload to cloud, get shareable URL |
| Pull context from cloud |
| List available souls |
| Search across souls |
| Generate share links |
Example Workflow:
# Upload your project.faf
faf_cloud_publish { soul_name: "my-project" }
→ https://mcpaas.live/souls/my-project
# Anyone can fetch it
faf_cloud_fetch { soul_name: "my-project" }
→ Context merged into local project.fafZero-install sharing - Recipients need no MCP setup. Served from 300+ Cloudflare edges with <1ms cold starts via 2.7KB Zig-WASM engine.
Eternal Bi-Sync
Your .faf file and your platform context files stay synchronized in milliseconds.
project.faf ←── 8ms ──→ .cursorrules / AGENTS.md / CLAUDE.md / GEMINI.md
Single source of truthUpdate either side → both stay aligned
--allflag syncs to all four formats at onceZero manual maintenance
Works across teams, branches, sessions
AI assistants forget. They drift. Every new session, AI starts guessing again. Bi-sync means context never goes stale.
Tier System: From Blind to Optimized
Tier | Score | Status |
🏆 TROPHY | 100% | AI never has to guess |
★ GOLD | 99%+ | 1 slot from Trophy |
◆ SILVER | 95%+ | Close — keep going |
◇ BRONZE | 85%+ | Interim — keep going |
● GREEN | 70%+ | Interim — keep going |
● 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.
use>faf | Prompt Pattern
Start every prompt with "Use FAF" to invoke MCP tools:
Use FAF to initialize my project
Use FAF to score my AI-readiness
Use FAF to sync my context
Use FAF to enhance my projectWorks on all platforms — stops web search, forces tool usage.
29 MCP Tools
Tool | Purpose |
| Initialize project.faf |
| Check AI-readiness (0-100%) |
| Sync context across platforms |
| Bi-directional .faf ↔ CLAUDE.md |
| Parse and validate FAF files |
| Create/update FAF with validation |
Interop Tools | |
| Import/export/sync AGENTS.md |
| Import/export/sync .cursorrules |
| Import/export/sync GEMINI.md |
| Import/export directory structure |
| Generate .faf from GitHub repo URL |
Cloud Tools | |
| Upload to mcpaas.live |
| Pull from cloud |
| List souls |
| Search souls |
| Generate share links |
Plus CLI fallback (via faf-cli):
faf readme- Extract 6 Ws from README (+25-35% boost)faf human-add- Non-interactive YAML merge (6Ws Builder)faf git- GitHub repo analysis without cloningAnd 40+ more commands...
Ecosystem
claude-faf-mcp — Claude Desktop (33 tools)
faf-cli — Terminal CLI
faf-wasm — WASM SDK (<5ms scoring)
faf.one — Official website
If faf-mcp has been useful, consider starring the repo — it helps others find it.
License
MIT License — Free and open source
Zero drift. Eternal sync. AI optimized. 🏆
"It's so logical if it didn't exist, AI would have built it itself" — Claude
Maintenance
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Wolfe-Jam/faf-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server