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.
Enables AI-powered querying of PDF documents using hybrid retrieval (BM25 + vector search) and retrieval-augmented generation, returning structured answers with source citations and confidence scores.
Enables document Q&A and knowledge retrieval through hybrid semantic and keyword search, with tools for document ingestion, chunking, summarization, PII redaction, and RAGAS-based evaluation.
Enables natural-language retrieval from a self-hosted documentation index, returning cited answers with deep links, and supports private corpora inaccessible on the public internet.