A private, self-hosted RAG service over MCP that enables document ingestion, hybrid retrieval (BM25 + dense vectors fused with RRF), and notebook management through 14 tools, keeping documents on your own hardware.
An MCP server that provides semantic search over a document corpus, enabling AI clients to retrieve and cite relevant chunks from indexed documents via RAG pipelines.
An MCP server for document parsing, ingestion, query (including multimodal), and lightweight knowledge graph inspection, enabling RAG workflows via the Model Context Protocol.