Enables MCP clients to search technical document collections using hybrid BM25 and embedding retrieval, returning cited page-level passages to support grounded, evidence-based answers.
Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.
Enables users to ingest documents, run retrieval-augmented queries with dense/sparse search and reranking, and inspect ingestion/query traces and evaluation results through MCP tools.
Enables agent tools like Claude Code and GitHub Copilot to perform knowledge retrieval using hybrid search (BM25 + dense) with reranking, via MCP protocol.
Enables any MCP host to search and answer over your own documents with hybrid BM25+dense retrieval, cross-encoder reranking, and grounded, cited responses that refuse when no evidence is found.