mcp-local-rag
"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨
How to use
The mcp-local-rag server is a "primitive" RAG-like web search model context protocol (MCP) server designed to run locally on your machine. Developers can utilize this tool to efficiently process queries without relying on external APIs, enabling faster iterations and a more controlled development environment. With its lightweight architecture, this server allows for easy experimentation with context-aware search capabilities directly from your local setup.
Once you have the mcp-local-rag server running, you can interact with it through the command line interface by sending context-based search queries. While there are no specific tools documented, you can utilize basic text queries to explore the server's capabilities. Commands work best when they are simple and directly related to your search needs, allowing you to test different contexts and see immediate results in your local environment.
How to install
To install the mcp-local-rag server, you will need to have Node.js installed on your machine. Here are the installation options:
Option A: Quick start with npx
If you want to quickly start using the server without a global installation, use the following command:
npx -y mcp-local-rag
Option B: Global install alternative
Alternatively, you can install the server globally with:
npm install -g mcp-local-rag
This will allow you to run the server from any directory in your terminal.
Additional notes
When configuring the mcp-local-rag server, ensure that your local environment has adequate permissions to bind to the designated ports. There are no specific environment variables required, but be mindful of potential conflicts with other local services running on the same port. If you encounter any issues, verify that the server is not already running in another terminal session.
Related MCP Servers
mcp-pinecone
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
Gitingest
mcp server for gitingest
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
microsoft_fabric_mcp
MCP server wrapping around the Fabric Rest API
mcp -memos-py
A Python package enabling LLM models to interact with the Memos server via the MCP interface for searching, creating, retrieving, and managing memos.
mcp -python-template
This template provides a streamlined foundation for building Model Context Protocol (MCP) servers in Python. It's designed to make AI-assisted development of MCP tools easier and more efficient.