mcp-local-rag and mcp-rag-server
These two tools appear to be **competitors**, as both are independent Model Context Protocol (MCP) servers designed to enable Retrieval Augmented Generation (RAG) capabilities for Large Language Models.
About mcp-local-rag
nkapila6/mcp-local-rag
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
Implements multi-engine web search across 9+ backends (DuckDuckGo, Google, Bing, Brave, Wikipedia) with semantic ranking using Google's MediaPipe text embeddings, extracting markdown from fetched URLs without external APIs. Exposes tools like `deep_research`, `deep_research_google`, and `rag_search_ddgs` as MCP resources compatible with Claude Desktop, Cursor, and other MCP clients. Deployable via `uvx` or Docker and includes Agent Skills that guide LLMs on query formulation and backend selection for privacy-aware or comprehensive research.
About mcp-rag-server
kwanLeeFrmVi/mcp-rag-server
mcp-rag-server is a Model Context Protocol (MCP) server that enables Retrieval Augmented Generation (RAG) capabilities. It empowers Large Language Models (LLMs) to answer questions based on your document content by indexing and retrieving relevant information efficiently.
Supports multiple embedding providers (OpenAI, Ollama, Granite, Nomic) with a SQLite-backed vector store, exposing indexing and retrieval operations as MCP tools and resources over stdio. Processes documents in five formats (.txt, .md, .json, .jsonl, .csv) with configurable chunking, enabling seamless integration into any MCP-compatible client or LLM application.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work