What is Mcp Rag Server

mcp-rag-server is a Model Context Protocol server that enables Retrieval Augmented Generation (RAG) by indexing documents and providing relevant context to Large Language Models through the MCP protocol.

Use cases

This tool is particularly useful for applications requiring efficient document retrieval based on user queries, enabling better responses and insights from Large Language Models by utilizing stored context from indexed documents.

How to use

To use the mcp-rag-server, install it globally via npm or clone the repository and build it from source. Set environment variables for the Base LLM API, embedding model, vector store path, and chunk size. Run the server using ‘mcp-rag-server’ or ‘npx mcp-rag-server’. Index documents using the provided MCP tools and query them as needed.

Key features

Key features include the ability to index multiple document formats, customizable chunk sizes, a local SQLite vector store, support for various embedding providers, and exposed MCP tools for seamless integration with clients.

Where to use

mcp-rag-server can be utilized in environments where Large Language Models are deployed, such as chatbots, virtual assistants, and knowledge management systems, enabling these systems to provide contextual responses based on indexed document content.

mcp-rag-server

A Model Context Protocol (MCP) server that enables Retrieval Augmented Generation (RAG). It indexes your documents and serves relevant context to Large Language Models via the MCP protocol.

Integration Examples

Generic MCP Client Configuration

{
  "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"
      }
    }
  }
}

Example Interaction

# Index documents
>> tool:embedding_documents {"path":"./docs"}

# Check status
>> resource:embedding-status

<< rag://embedding/status
Current Path: ./docs/file1.md
Completed: 10
Failed: 0
Total chunks: 15
Failed Reason:

Table of Contents

• Integration Examples
• Features
• Installation
• Quick Start
• Configuration
• Usage
  • MCP Tools
  • MCP Resources
• How RAG Works
• Development
• Contributing
• License

Features

• 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

From npm

npm install -g mcp-rag-server

From Source

git clone https://github.com/kwanLeeFrmVi/mcp-rag-server.git
cd mcp-rag-server
npm install
npm run build
npm start

Quick Start

export BASE_LLM_API=http://localhost:11434/v1
export EMBEDDING_MODEL=granite-embedding-278m-multilingual-Q6_K-1743674737397:latest
export VECTOR_STORE_PATH=./vector_store
export CHUNK_SIZE=500

# Run (global install)
mcp-rag-server

# Or via npx
npx mcp-rag-server

💡 Tip: We recommend using Ollama for embedding. Install and pull the nomic-embed-text model:

ollama pull nomic-embed-text
export EMBEDDING_MODEL=nomic-embed-text

Configuration

Variable	Description	Default
BASE_LLM_API	Base URL for embedding API	http://localhost:11434/v1
LLM_API_KEY	API key for your LLM provider	(empty)
EMBEDDING_MODEL	Embedding model identifier	nomic-embed-text
VECTOR_STORE_PATH	Directory for local vector store	./vector_store
CHUNK_SIZE	Characters per text chunk (number)	500

💡 Recommendation: Use Ollama embedding models like nomic-embed-text for best performance.

Usage

MCP Tools

Once running, the server exposes these tools via MCP:

• embedding_documents(path: string): Index documents under the given path
• query_documents(query: string, k?: number): Retrieve top k chunks (default 15)
• remove_document(path: string): Remove a specific document
• remove_all_documents(confirm: boolean): Clear the entire index (confirm=true)
• list_documents(): List all indexed document paths

MCP Resources

Clients can also read resources via URIs:

• rag://documents — List all document URIs
• rag://document/{path} — Fetch full content of a document
• rag://query-document/{numberOfChunks}/{query} — Query documents as a resource
• rag://embedding/status — Check current indexing status (completed, failed, total)

How RAG Works

1. Indexing: Reads files, splits text into chunks based on CHUNK_SIZE, and queues them for embedding.
2. Embedding: Processes each chunk sequentially against the embedding API, storing vectors in SQLite.
3. Querying: Embeds the query and retrieves nearest text chunks from the vector store, returning them to the client.

Development

npm install
npm run build      # Compile TypeScript
npm start          # Run server
npm run watch      # Watch for changes

Contributing

Contributions are welcome! Please open issues or pull requests on GitHub.

License

MIT 2025 Quan Le