mcp-server and claude-faf-mcp
These are ecosystem siblings—both are MCP servers that extend Claude's capabilities through different execution environments (E2B's sandboxed code execution vs. FAF's domain-specific format processing), allowing users to choose the appropriate integration based on their use case.
About mcp-server
e2b-dev/mcp-server
Giving Claude ability to run code with E2B via MCP (Model Context Protocol)
Implements isolated code execution through E2B's sandboxed environment, enabling Claude to run and test code snippets across multiple languages without local system access. Supports both JavaScript and Python implementations with Smithery integration for seamless Claude Desktop installation. Uses the MCP stdio transport protocol to establish real-time communication between Claude and the E2B code interpreter backend.
About claude-faf-mcp
Wolfe-Jam/claude-faf-mcp
Anthropic MCP server for .faf — 33 tools, IANA-registered format. npm: claude-faf-mcp. MCP Registry #2759
Provides 33 MCP tools for creating and managing `.faf` files—a YAML format that captures project context (who it's for, what it does, why it exists) to optimize AI understanding across sessions. Features bi-directional and tri-directional sync with `CLAUDE.md` and `MEMORY.md`, auto-detection of project stacks, AI-readiness scoring (0-100%), and interoperability with other LLM platforms (Gemini, Grok, Cursor) through a shared `.faf` specification. Runs entirely locally with zero dependencies, averaging 19ms per tool execution, and uses stdio transport for Claude Desktop integration.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work