rag-mcp

zcutlip/rag-mcp

★ 0 stars Python AI/LLM Updated today

MCP server exposing RAG tools backed by Ollama embeddings and ChromaDB

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

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

Add to claude_desktop_config.json:

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

Or install with pip: pip install rag-mcp

README Excerpt

An MCP server that exposes tools for ingesting document chunks and retrieving relevant context for RAG (Retrieval-Augmented Generation). Embeddings are generated via a local [Ollama](https://ollama.com) instance, and vectors are persisted in [ChromaDB](https://www.trychroma.com/). - Python >= 3.10 - [Ollama](https://ollama.com) running locally

Tools (6)

CHROMA_PERSIST_DIROLLAMA_HOSTOLLAMA_MODELRAG_INGEST_COLLECTIONRAG_INGEST_DIRadd_documents

rag-mcp

Quick Install

README Excerpt

Tools (6)

Related AI/LLM Servers