Best MCP Servers for RAG & Knowledge Retrieval (2026)

🎖️ 🦀 🏠 🍎 Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, semantic search, LLM-powered history analysis, and event-triggered actions - enables building c

📇 🏠 - Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources

📇 🏠 - Universal memory service providing semantic search, persistent storage, and autonomous memory consolidation

🐍 ☁️ 🏠 - Production-ready RAG platform combining Graph RAG, vector search, and full-text search. Best choice for building your own Knowledge Graph and for Context Engineering

The official Redis MCP Server is a natural-language interface for managing and searching data in Redis from MCP clients. It provides string, hash, list, set, and sorted set tools, pub/sub and Streams tools, JSON document tools, vector index management and vector search through its query engine tools, a tool to search Redis documentation, and a server management tool.

MCP server that provides up-to-date documentation for a specific Rust crate to LLM coding assistants. Each instance fetches one crate's documentation, generates embeddings for semantic search, and exposes a query_rust_docs tool that answers questions using summaries of the retrieved docs; multiple instances can run at once for different crates, and an OpenAI API key is required for embeddings and summarization.

🐍 🏠 - An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentatio

📇 🏠 - Privacy-first document search server running entirely locally. Supports semantic search over PDFs, DOCX, TXT, and Markdown files with LanceDB vector storage and local embeddings - no API keys

Shodh-Memory is persistent cognitive memory for AI agents and robots that runs as a single binary with no LLM in the loop, no API keys, and no external databases, so it works fully offline. Storing and recalling memories uses local algorithms only: on-device embeddings, a cross-encoder reranker, and local entity and relation extraction that builds a typed knowledge graph; memories that are used often become easier to recall (Hebbian learning) while irrelevant ones decay. It connects to agents over MCP/HTTP and to robots over Zenoh/ROS2.

📇 ☁️ - An MCP server for Apify's open-source RAG Web Browser Actor to perform web searches, scrape URLs, and return content in Markdown.

☕ 🐍 ☁️ - MCP service for Tablestore, features include adding documents, semantic search for documents based on vectors and scalars, RAG-friendly, and serverless.

🏠 🐍 - "primitive" RAG-like web search model context protocol (MCP) server that runs locally. No APIs needed.

🐍 🏠 🍎 🪟 🐧 - Persistent memory for AI coding agents with semantic search, auto-capture, cross-session learning, and intelligent forgetting. 12 MCP tools, local-first.

📇 ☁️ - Retrieve context from your (RAG) knowledge base connected to integrations like Google Drive, Notion, JIRA and more.

](https://glama.ai/mcp/servers/elvismdev/mem0-mcp-selfhosted) 🐍 🏠 🍎 🪟 🐧 - Self-hosted mem0 MCP server for Claude Code with Qdrant vector search, Neo4j knowledge graph, and Ollama embeddings. Zero

](https://glama.ai/mcp/servers/lyonzin/knowledge-rag) 🐍 🏠 🍎 🪟 🐧 - Local RAG system for Claude Code with hybrid search (BM25 + semantic), cross-encoder reranking, markdown-aware chunking, query ex

](https://glama.ai/mcp/servers/@aitytech/agentkits-memory) 📇 🏠 🍎 🪟 🐧 - Persistent memory for AI coding assistants with hybrid search (FTS5 + vector embeddings), session tracking, automatic contex

🐍 🏠 - Modern, secure MCP server for accessing ZIM format knowledge bases offline. Enables AI models to search and navigate Wikipedia, educational content, and other compressed knowledge archives wit