MCPquality 0.75
Haiku RAG
Agentic RAG system powered by LanceDB, Pydantic AI, and Docling
What it does
Agentic RAG system powered by LanceDB, Pydantic AI, and Docling
Retrieval-augmented generation system providing hybrid search combining vector and full-text search with Reciprocal Rank Fusion. Features multi-agent research workflows for planning, searching, evaluating, and synthesizing information with citations. Supports 40+ file formats including PDF, DOCX, HTML, and Markdown. Works locally with embedded LanceDB or supports cloud storage on S3, GCS, and Azure.
Capabilities
mcptransport-stdioopen-source
Server
Quality
0.75/ 1.00
deterministic score 0.75 from registry signals: · indexed on pulsemcp · has source repo · 524 github stars · registry-generated description present
Provenance
Indexed frompulsemcp
Enriched2026-05-15 05:22:22Z · deterministic:mcp:v1 · v1
First seen2026-04-25
Last seen2026-05-15