A complete MCP server for Retrieval-Augmented Generation with file management and vector memory for agents. Supports multiple document formats (PDF, DOCX, TXT, MD, CSV, JSON) with semantic search using Hugging Face embeddings and ChromaDB for efficient vector storage.
A MCP server for document ingestion and semantic search using ChromaDB and sentence transformers, enabling users to query natural language over ingested documents.
A local MCP server that answers natural language questions over a collection of research PDFs, using semantic retrieval and Gemini for grounded answers with citations.