kwanLeeFrmVi/mcp-rag-server
If you are the rightful owner of mcp-rag-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol (MCP) server that enables Retrieval Augmented Generation (RAG) by indexing documents and serving relevant context to Large Language Models.
The mcp-rag-server is a specialized server designed to facilitate Retrieval Augmented Generation (RAG) by indexing documents and providing relevant context to Large Language Models (LLMs) through the Model Context Protocol (MCP). It supports various document formats and allows for customizable text chunking, making it versatile for different use cases. The server is built to integrate seamlessly with MCP clients, offering tools and resources over standard input/output. It leverages a local vector store powered by SQLite, utilizing LangChain's LibSQLVectorStore, and supports multiple embedding providers, including OpenAI, Ollama, Granite, and Nomic. This makes it a robust solution for applications requiring efficient document indexing and retrieval.
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
Usages
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"
}
}
}
}
