A
licenseA
qualityA
maintenance.FAF (Foundational AI-context Format) with 50+ tools - Only Persistent project context that integrates seamlessly with Claude Desktop workflows. Officially merged (#2759) Anthropic MCP server.
14
313 npm
23
MIT
grok-faf-mcp
by Wolfe-Jam
Related Servers
Alternatives to grok-faf-mcp
- AlicenseNot gradedqualityAmaintenancePersistent project context in Rust. 8 MCP tools via rmcp SDK — parse, validate, score, compress, discover, and token analysis. Single binary, zero config. IANA-registered format (application/vnd.faf+yaml). One file, every AI platform.109 npm4MIT
- AlicenseAqualityAmaintenancePersistent project context for Google Gemini. 12 MCP tools for .faf Project DNA — auto-detect your stack, validate, score, and sync across CLAUDE.md, GEMINI.md, and AGENTS.md. Python/FastMCP. IANA-registered format (application/vnd.faf+yaml). 183 tests. One file, every AI platform.13171 PyPI2MIT
- AlicenseAqualityAmaintenancePersistent project context MCP server that syncs a single .faf file to all AI tool formats (Cursor, Windsurf, Cline, etc.), enabling eternal bi-sync and optimized context for AI assistants.15905 npm7MIT
Related Servers
- AlicenseAqualityBmaintenanceMCP server that gives AI agents xAI Grok video generation — submit a prompt, poll the render, download the clip. Works with OpenCode, Claude Desktop, Cursor, VS Code, and any MCP client.4MIT
- AlicenseAqualityAmaintenanceUse XAI's latest api functionalities with Grok MCP. It supports image understanding and generation, live search, latest models and more.2252MIT
- AlicenseAqualityCmaintenanceMCP server that converts URLs to clean Markdown/Text for LLM agents.2533 npm5MIT
- FlicenseNot gradedqualityCmaintenanceMCP server for the xAI Grok API, providing tools for chat completions, vision analysis, web/X search, embeddings, and model listing via stdio.-
- AlicenseAqualityAmaintenanceAn MCP server that fetches any URL and returns clean Markdown, plus web search with real links.2Apache 2.0
- AlicenseNot gradedqualityBmaintenanceA dead simple MCP server for exposing your app functions to AI agents like Claude Desktop.6 npm6MIT
TDQS
A4.1/5.0
Scored across 12 tools
Disambiguation4/5
Tools are generally distinct across the three subsystems (faf, rag, refresh), but there is some overlap between refresh_faf and refresh_blend—refresh_blend always fires both refresh_faf and refresh_fafm, so an agent might wonder whether to use refresh_faf alone or the compound tool. However, descriptions are clear enough to prevent major confusion.
Naming Consistency5/5
All tool names follow a consistent snake_case pattern with a clear subsystem prefix (faf_, rag_, refresh_). The naming is uniform and predictable, making it easy to infer the action and resource.
Tool Count5/5
With 12 tools, the server is well-scoped. Each tool serves a distinct function within its subsystem, and the count feels appropriate for the domain of project context management and RAG caching—not too few, not too many.
Completeness4/5
The tool surface covers initialization, scoring, syncing, validation, orchestration, and refresh for the FAF context, plus cache management for RAG. Minor gaps exist, such as the absence of an explicit update or delete for the project.faf file (though force overwrite exists) and no tool to configure RAG parameters.
Maintenance
ActivityActive
ResponsivenessResponsive