$ loading_
Index documents and retrieve knowledge via keyword and vector search over MCP.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "rag-mcp" yet — see the docs or source repo.
Use rag-mcp to index my product documentation and show how to find content about 'permission management' with both keyword and vector search.
A retrieval workflow description after indexing, plus example relevant results from both keyword and vector search.
I want to build a Q&A assistant over internal company materials. Use rag-mcp to explain how to ingest documents, create indexes, and retrieve the most relevant passages for a question.
Document ingestion and indexing steps, along with retrieved relevant passages for a sample question.
Using rag-mcp, run both keyword and vector search on the same set of technical documents and compare the result differences for the query 'API rate limiting strategy'.
A comparison of both retrieval results to help judge which method fits different query scenarios.
Index documents and retrieve relevant context for better LLM responses.
Let AI securely query private local documents with persistent memory.
Search and add traceable RAG knowledge for each project workspace.
Retrieve and process docs with vector search to enrich AI responses.
Retrieve relevant context and metadata from Qdrant using natural language queries.
Use authenticated MCP tools for graph-augmented and hybrid RAG retrieval.