Think of this as a routing layer for retrieval tools. It indexes RAG-focused MCP servers from the official registry, enriches them with metadata like domain (docs, code, web), retrieval method (dense, sparse, hybrid), and reachability status, then helps you pick the right one. You get four MCP tools: rag_find_servers for search and filtering, rag_get_server for details, rag_list_categories, and rag_explain_score. It doesn't do retrieval itself. Instead, it answers "which retrieval server should I use?" based on constraints like citations support, privacy requirements, or freshness. The hosted API at ragmap-api.web.app runs probes to verify streamable-http endpoints are actually reachable, and supports semantic search when OpenAI embedding is configured. Useful when you're building a RAG pipeline and need to discover or programmatically select from dozens of retrieval options.
claude mcp add --transport stdio khalidsaidi-ragmap uvx ragmap