"Exploring RAG through defined workspaces" matching MCP servers:

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

Enables ingestion and semantic search over text documents using PostgreSQL + pgvector and OpenAI-compatible embeddings, allowing any LLM agent to retrieve relevant chunks for grounded answers.

RAG Vault lets your AI coding assistant search your private documents locally. Everything runs on your machine and your data stays private.

Enables Claude to search a local hybrid retrieval index of research papers and ingest new PDFs, providing research-paper memory queryable directly through natural language.

Intelligent knowledge base system that enables users to process documents in 25+ formats, perform semantic search and Q\&A through vector retrieval. Supports multiple AI models including OpenAI and DouBao with local processing capabilities.

MCP bridge to a multimodal RAG service, enabling hybrid search and Q&A over documents with tools for knowledge base queries and health checks.

Keyless local RAG over your own documents (ChromaDB) with traceable citations, exposed as MCP tools and a FastAPI endpoint.

Provides local Retrieval-Augmented Generation (RAG) capabilities using Ollama for embeddings and ChromaDB for vector storage. It enables users to ingest and perform semantic searches across PDF, Markdown, and TXT documents within MCP-compatible clients.

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.

Provides RAG tools with local vector retrieval and web fallback using Firecrawl, enabling document ingestion and querying through MCP stdio transport.

A Retrieval Augmented Generation system that enables AI assistants to perform semantic searches and manage document indices for markdown files. It supports PostgreSQL with pgvector and integrates both Google Gemini and Ollama for intelligent embedding generation.

Enables read-only semantic search over a local document corpus with on-device embeddings and a local Chroma store, featuring symlink-hardened file access and structured error handling.

A minimal RAG service that exposes a vector index for document retrieval via REST and MCP, allowing querying for relevant document chunks and returning a suggested LLM prompt.

A modular RAG server with hybrid search and LLM rerank, exposing 3 MCP tools for AI clients like Claude Desktop and Cursor.

A privacy-preserving local RAG system integrated with MCP, enabling natural language queries over ingested documents and a SQLite database through vector search and local database tools.

RAG document search MCP server that allows AI assistants to search a local document set and retrieve grounded passages via keyword (SQLite FTS5) or semantic (Chroma) backends.

Enables any MCP-capable LLM client to search self-hosted long-term memory over markdown and PDF documents, combining dense semantic vectors with BM25 keyword retrieval and optional cross-encoder reranking. Exposes a read-only tool surface for querying incidents, runbooks, and other knowledge-base content, while writes happen out-of-band through ingestion jobs or a token-gated internal API.

A Model Context Protocol (MCP) server for Retrieval-Augmented Generation (RAG) operations. It provides tools for building and querying vector-based knowledge bases from document collections, enabling semantic search and document retrieval capabilities.

Enables indexing a folder of documents or uploaded files into a Qdrant vector store and retrieving relevant chunks with cosine similarity, metadata filters, and heuristic reranking. Exposes rag_stats, rag_search, and rag_index tools over HTTP and Streamable HTTP MCP so clients can fetch ready-to-use context blocks without any built-in chat model.