Enables MCP clients to search a Postgres/pgvector RAG index of documents, fetch a full document by ID, and list available documents through three read-only tools, with provenance (doc ID, chunk, heading, score) on every hit and untrusted-corpus safeguards. Retrieval quality is measurable via a reproducible hit@k/MRR evaluation.
Exposes a RAG document-search API as MCP tools (rag_health, rag_ingest, rag_query), enabling agents to index and search markdown documents with cited results through natural language.
Enables MCP clients to search and read a local folder of Markdown documentation through BM25-ranked, heading-aware tools, and to answer questions from it with numbered citations. It grounds assistant responses in the exact documentation sections instead of relying on model memory.
Enables semantic search over a software project's Markdown and text documentation by indexing document chunks in Qdrant and exposing retrieval through MCP tools.
Enables indexing a Markdown knowledge base with local sentence embeddings and serving retrieval over MCP, allowing LLM clients to query the indexed knowledge.