MCP Server for RAG Retrieval

A generic Retrieval-Augmented Generation (RAG) Model Context Protocol (MCP) server with pluggable embedding providers and vector stores.

Why this server?

Vendor MCP servers usually only support their (own) integrated embedding models. If your index uses external embeddings (e.g., OpenAI), those servers can't query it. This server fills that gap — it embeds your query with the provider of your choice, then searches any supported vector store.

Related MCP server: OpenAI Vector Store MCP Server

Currently Supports

Embedding Providers:

• OpenAI (text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002, etc.)

Vector Stores:

• Pinecone

• pgvector (PostgreSQL)

Tools

retrieve

Search a knowledge base and return relevant content.

Parameters:

• query (string, required) — The search query to find relevant content.

Returns a JSON array of results, each with text, score, and metadata fields.

Install & Run

Run directly with uvx (no install needed):

uvx rag-retrieval-mcp[all]

Or install with pip:

pip install rag-retrieval-mcp[all]
rag-retrieval-mcp

MCP client configuration

{
  "mcpServers": {
    "rag-retrieval": {
      "command": "uvx",
      "args": ["rag-retrieval-mcp[all]"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "PINECONE_API_KEY": "your-pinecone-api-key",
        "PINECONE_HOST": "your-pinecone-index-host-url"
      }
    }
  }
}

Environment Variables

Adding New Providers

Implement the EmbeddingProvider or VectorStore abstract base class and register it in server.py's factory function. See src/rag_retrieval_mcp/embedding_providers/base.py and src/rag_retrieval_mcp/vector_stores/base.py for the interfaces.

License

Apache License 2.0