faf-mcp
Universal persistent project context server - IANA-registered .FAF format
MCP 服务配置
复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用
{
"mcpServers": {
"faf-mcp": {
"args": [
"faf-mcp@1.2.4"
],
"command": "npx"
}
}
}可用工具 （5 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
tavily_search 14 个参数 需填 1 项
Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
必填参数：query
tavily_extract 6 个参数 需填 1 项
Extract content from URLs. Returns raw page content in markdown or text format.
必填参数：urls
tavily_crawl 11 个参数 需填 1 项
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
必填参数：url
tavily_map 8 个参数 需填 1 项
Map a website's structure. Returns a list of URLs found starting from the base URL.
必填参数：url
tavily_research 2 个参数 需填 1 项
Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.
必填参数：input
服务介绍
.FAF optimizes AI for your codebase. At 100% (Gold Code), AI stops guessing and starts knowing. Universal MCP server for Cursor, Windsurf, Cline, VS Code, and all MCP-compatible platforms.
Universal version of claude-faf-mcp 鈥� Anthropic-approved MCP server, now compatible with all platforms.
The Problem: Context-Drift
AI assistants forget. They misunderstand. They drift.
Every new session, every new file, every new developer 鈥� AI starts guessing again. Your codebase context leaks away. Yesterday's perfect assistant becomes today's confused intern.
.FAF fixes this permanently.
The Solution: Gold Code
鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹�
馃弳 FAF AI-READINESS SCORE: 100/100 鈥� GOLD CODE
鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹�
At 100%, AI is optimized. No more guessing.
Peak AI performance activated.
鈹溾攢 Project DNA locked in 鈹溾攢 Zero context-drift
鈹溾攢 Architecture understood 鈹溾攢 Eternal bi-sync active
鈹溾攢 Domain model captured 鈹溾攢 Team alignment permanent
鈹斺攢 Every session starts smart 鈹斺攢 AI works WITH you, not around you
鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹佲攣鈹�
馃拵 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 鈥� 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.
鈿� Quick Start
1. Install:
npm install -g faf-mcp
2. Add to your MCP config:
{"mcpServers": {"faf": {"command": "npx", "args": ["-y", "faf-mcp"]}}}
Platform-Specific Setup
| Platform | Config File |
|---|---|
| Cursor | ~/.cursor/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| Cline | Cline MCP settings |
| VS Code | MCP extension config |
| Claude Desktop | Use claude-faf-mcp |
馃攧 Eternal Bi-Sync
The magic: .faf 鈫� CLAUDE.md stay synchronized in milliseconds.
project.faf 鈫愨攢鈹�鈹�鈹� 8ms 鈹�鈹�鈹�鈹�鈫� CLAUDE.md
鈹� 鈹�
鈹斺攢鈹� Single source of truth 鈹�鈹�鈹�
- Update either file 鈫� both stay aligned
- Zero manual maintenance
- Works across teams, branches, sessions
- Context never goes stale
Tier System: From Blind to Optimized
| Tier | Score | Status |
|---|---|---|
| 馃弳 Trophy | 100% | AI Optimized 鈥� Gold Code |
| 馃 Gold | 99%+ | Near-perfect context |
| 馃 Silver | 95%+ | Excellent |
| 馃 Bronze | 85%+ | Production ready |
| 馃煝 Green | 70%+ | Solid foundation |
| 馃煛 Yellow | 55%+ | AI flipping coins |
| 馃敶 Red | <55% | AI working blind |
| 馃 White | 0% | No context at all |
At 55%, AI is guessing half the time. At 100%, AI is optimized.
馃挰 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 project
Works on all platforms 鈥� stops web search, forces tool usage.
馃洜锔� 17 Native MCP Tools
| Tool | Purpose |
|---|---|
faf_init |
Initialize project.faf |
faf_score |
Check AI-readiness (0-100%) |
faf_sync |
Sync context across platforms |
faf_bi_sync |
Bi-directional .faf 鈫� CLAUDE.md |
faf_enhance |
Intelligent enhancement |
faf_read |
Parse and validate FAF files |
faf_write |
Create/update FAF with validation |
Plus CLI fallback with 40+ commands.
馃幆 The .FAF Position
Platform Context Protocol
鈹�鈹�鈹�鈹�鈹�鈹�鈹�鈹� 鈹�鈹�鈹�鈹�鈹�鈹�鈹� 鈹�鈹�鈹�鈹�鈹�鈹�鈹�鈹�
Cursor 鈫� .faf 鈫� MCP
Windsurf 鈫� .faf 鈫� MCP
Cline 鈫� .faf 鈫� MCP
VS Code 鈫� .faf 鈫� MCP
Claude 鈫� .faf 鈫� MCP
Any IDE 鈫� .faf 鈫� MCP
.FAF is the foundational layer. Universal context format. IANA-registered. Works everywhere.
馃摝 Ecosystem
- claude-faf-mcp 鈥� Claude Desktop (52 tools)
- faf-cli 鈥� Terminal CLI (18k+ downloads)
- faf-wasm 鈥� WASM SDK (<5ms scoring)
- faf.one 鈥� Official website
馃搫 License
MIT License 鈥� Free and open source
Zero drift. Eternal sync. AI optimized. 馃弳
"It's so logical if it didn't exist, AI would have built it itself" 鈥� Claude
