MCP MCP Server

mcp-rag-server is a Model Context Protocol (MCP) server that enables Retrieval Augmented Generation (RAG) capabilities. It empowers Large Language

Local serverstdioTypeScript

What is the MCP MCP server?

If you already use MCP, the mcp mcp server is the piece that lets your assistant work with it directly. 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.

What the server does

  • Index documents in .txt, .md, .json, .jsonl, and .csv formats
  • Customizable chunk size for splitting text
  • Local vector store powered by SQLite (via LangChain's LibSQLVectorStore)
  • Supports multiple embedding providers (OpenAI, Ollama, Granite, Nomic)
  • Exposes MCP tools and resources over stdio for seamless integration with MCP clients

Installation

npx on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Credentials and setup notes

Configuration is passed through the environment: BASE_LLM_API, EMBEDDING_MODEL, VECTOR_STORE_PATH, CHUNK_SIZE, LLM_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by kwanLeeFrmVi; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

How to install the MCP MCP server

{
  "mcpServers": {
    "rag": {
      "command": "npx",
      "args": ["-y", "mcp-rag-server"],
      "env": {
        "BASE_LLM_API": "http://localhost:11434/v1",
        "EMBEDDING_MODEL": "nomic-embed-text",
        "VECTOR_STORE_PATH": "./vector_store",
        "CHUNK_SIZE": "500"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
BASE_LLM_APIConfiguration value read at startup.Optional
EMBEDDING_MODELConfiguration value read at startup.Optional
VECTOR_STORE_PATHFilesystem location the server is allowed to use.Optional
CHUNK_SIZEConfiguration value read at startup.Optional
LLM_API_KEYCredential the server authenticates with.Yes

Frequently asked questions

The server supports OpenAI, Ollama, Granite, and Nomic. Ollama with the `nomic-embed-text` model is recommended for best performance.