DOCS BLOG ABOUT TRY THE GATEWAY

// MCP TOOL REFERENCE

FAF TOOLS

32 tools from the Faf MCP Server, categorised by risk level.

View the Faf policy →

// ALL 32 FAF TOOLS

READ 26 tools

Read faf_about Learn what .faf format is - project DNA for AI 🧡⚡️ Read faf_agents Import/Export/Sync between AGENTS.md (OpenAI/Codex) and project.faf - AI interop! Read faf_auto 🏎️ ONE COMMAND TO RULE THEM ALL - Zero to Championship AI context instantly! Runs init + sync + formats + ... Read faf_bi_sync Bi-directional sync between project.faf and CLAUDE.md. v4.5.0: Also sync to AGENTS.md, .cursorrules, GEMINI... Read faf_check 🔍 Quality inspection for human_context fields + field protection - Shows empty/generic/good/excellent rati... Read faf_conductor Import/Export between conductor/ directory (Google Conductor) and project.faf - AI interop! Read faf_cursor Import/Export/Sync between .cursorrules (Cursor IDE) and project.faf - AI interop! Read faf_debug Debug faf-mcp environment - show working directory, permissions, and FAF CLI status Read faf_dna 🧬 Show your FAF DNA journey - See your evolution from birth to championship (22% → 85% → 99%) 🧡⚡️ Read faf_doctor 🏥 Health check for your .faf setup - Diagnose and fix common issues 🧡⚡️ Read faf_enhance Enhance project.faf (project DNA for AI) with AI optimization - SPEEDY AI you can TRUST! 🧡⚡️ Read faf_formats 😽 TURBO-CAT format discovery - Discovers all formats in your project (154+ validated types!) and fills sta... Read faf_friday 🎉 Friday Features - Chrome Extension detection, fuzzy matching & more! 🧡⚡️ Read faf_gemini Import/Export/Sync between GEMINI.md (Google Gemini CLI) and project.faf - AI interop! Read faf_git Generate project.faf from any GitHub repo URL - 1-click context extraction! Read faf_go 🎯 Guided interview to Gold Code - Claude asks questions till you hit 100%! Returns questions for missing f... Read faf_guide FAF MCP usage guide for your MCP host - Projects convention, path resolution, and UX patterns Read faf_list List directories and discover projects with project.faf files - Essential for FAF discovery workflow Read faf_quick ⚡ Lightning-fast .faf creation - One-liner format: "name, description, language, framework, hosting" 🧡⚡️ Read faf_read Read content from any file on the local filesystem Read faf_readme 📖 Extract 6 Ws (Who/What/Why/Where/When/How) from README.md into human_context - Smart pattern matching 🧡⚡️ Read faf_score Calculate your project's AI-readability from project.faf (project DNA for AI) - F1-inspired metrics! 🧡⚡️ Read faf_status Check if your project has project.faf (project DNA for AI) - Shows AI-readability status 🧡⚡️ Read faf_sync Sync project.faf (project DNA for AI) with CLAUDE.md - Bi-directional context 🧡⚡️ Read faf_trust Validate project.faf integrity - Trust metrics for project DNA for AI 🧡⚡️ Read faf_what What is .faf format? Quick explanation of project DNA for AI 🧡⚡️

WRITE 4 tools

Write faf_context 📂 Set or view active project context - Path is remembered for subsequent faf_ calls 🧡⚡️ Write faf_human_add 🧡 Add a human_context field (who/what/why/where/when/how) - Non-interactive for MCP 🧡⚡️ Write faf_init Create project.faf (project DNA for AI) - Makes your project instantly AI-readable 🧡⚡️. Just enter path or... Write faf_write Write content to any file on the local filesystem

DESTRUCTIVE 1 tools

Destructive faf_clear Clear caches, temporary files, and reset FAF state for a fresh start

EXECUTE 1 tools

Execute faf_chat 🗣️ Natural language project.faf generation - Ask 6W questions (Who/What/Why/Where/When/How) to build compl...

// RUNNING THIS SERVER

The managed route: connect Faf through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y faf-mcp

// FAQ

How many tools does the Faf MCP server have? +

The Faf MCP server exposes 32 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Faf tools? +

Route the Faf server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Faf tools fall into? +

Faf tools are categorised as Read (26), Write (4), Destructive (1), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.