MCP RAG Server

by sylphlab

AI/Data & Knowledge RAG Genkit ChromaDB Ollama

The mcp-rag-server is a Model Context Protocol (MCP) server that enables Retrieval Augmented Generation (RAG) capabilities for connected LLMs. It indexes documents from your project and provides relevant context to enhance LLM responses.

View on GitHub

Last updated: N/A

What is MCP RAG Server?

The MCP RAG Server is a server designed to provide Retrieval Augmented Generation (RAG) capabilities to Language Learning Models (LLMs) using the Model Context Protocol (MCP). It leverages local models (Ollama) and vector stores (ChromaDB) to index project documents and provide relevant context for enhanced LLM responses.

How to use MCP RAG Server?

The server is designed to be used with Docker Compose. After cloning the repository, you can start the services using docker-compose up -d --build. Then, you need to pull the embedding model using docker exec ollama ollama pull nomic-embed-text. Finally, configure your MCP client to connect to the server.

Key features of MCP RAG Server

Seamless MCP Integration
Local Control (Ollama and ChromaDB)
Automatic Context Indexing
Extensible (Built with Genkit)

Use cases of MCP RAG Server

Enhancing LLM responses with project-specific context
Providing RAG capabilities within a local and private environment
Integrating RAG functionality into MCP-based applications
Automatically indexing and querying project documentation

FAQ from MCP RAG Server

What is MCP?

MCP stands for Model Context Protocol, a standard for communication between LLMs and external services.

What is ChromaDB?

ChromaDB is a vector database used for storing and querying document embeddings.

What is Ollama?

Ollama is a tool for running and managing local language models.

How do I configure the server?

The server is configured using environment variables, typically set in the docker-compose.yml file.

What file types are supported for indexing?

The server supports indexing .txt, .md, code files, .json, .jsonl, and .csv files.