mcp-rag-server

ZainRafeeque/mcp-rag-server

★ 0 stars Python 🤖 AI/LLM Updated today

MCP server with local RAG (semantic search over a docs folder). FastMCP + fastembed, CPU-only, no API keys.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-rag-server": {
      "command": "uvx",
      "args": [
        "mcp-rag-server"
      ]
    }
  }
}

Or install with pip: pip install mcp-rag-server

README Excerpt

A small, self-contained **Model Context Protocol** server that does **local semantic search** over a folder of text documents. Drop in any `.md` or `.txt` files, point Claude Desktop (or any MCP host) at it, and ask questions. It demonstrates all three MCP primitives — **tool**, **resource**, **prompt** — and a complete RAG pipeline (chunk → embed → index → retrieve) running entirely on CPU with no API keys.

Tools (2)

search_docssummarize_doc

mcp-rag-server

Quick Install

README Excerpt

Tools (2)

Related AI/LLM Servers