mcp-rag-server and supernova-mcp-rag
The `shabib87/supernova-mcp-rag` project appears to be a practical proof-of-concept demonstrating how to build and run a local Model Context Protocol (MCP) server for Retrieval-Augmented Generation (RAG), which could potentially integrate with or be inspired by the architecture of the `kwanLeeFrmVi/mcp-rag-server`, making them ecosystem siblings where one is a specific implementation or example related to the broader capability offered by the other.
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.
About supernova-mcp-rag
shabib87/supernova-mcp-rag
A practical POC demonstrating how to build and run a local MCP server with Retrieval-Augmented Generation (RAG) for semantic search over internal documentation. Leverages Node.js, TypeScript, Hugging Face embeddings, and an in-memory vector store to enable fast, context-aware answers in tools like Cursor.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work