An MCP server that provides a search_docs tool with hybrid retrieval (BM25 + dense vectors) and cross-encoder reranking, backed by evaluation, prompt-injection guardrails, and OpenTelemetry tracing.
Exposes retrieval capabilities of two RAG systems as authenticated MCP tools, allowing any MCP client to perform graph-augmented and hybrid retrieval with JWT auth.
Enables agent tools like Claude Code and GitHub Copilot to perform knowledge retrieval using hybrid search (BM25 + dense) with reranking, via MCP protocol.
Exposes hybrid retrieval (dense embeddings + BM25 + RRF) and document operations (search, fetch, rerank) as MCP tools, using Qdrant and OpenAI embeddings for local or server mode.
Exposes document retrieval as an MCP tool, enabling LLMs to search a local vector store of markdown documents. Includes a retrieval evaluation harness to measure hit rate and MRR.