LocalFile-MCP-Server

DRITI2906/LocalFile-MCP-Server

3.1

If you are the rightful owner of LocalFile-MCP-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 dayong@mcphub.com.

The MCP RAG Server is designed to facilitate the analysis and retrieval of information from local files using the Model Context Protocol.

MCP RAG Server for Local File Analysis

This project implements a Model Context Protocol (MCP) server for Retrieval-Augmented Generation (RAG) that analyzes local files on your desktop. It exposes tools and resources for AI applications to query and retrieve information from your local files.

Features

  • Analyze and index local files (text, PDF, etc.)
  • Expose file search and retrieval tools via MCP
  • Compatible with Claude Desktop, VS Code, and other MCP clients

Quickstart

  1. Ensure you have Python 3.9+ and uv installed (uv installation guide).

  2. Install dependencies: powershell uv venv .venv\Scripts\activate uv pip install mcp fastapi pydantic numpy sentence-transformers faiss-cpu python-dotenv

  3. Run the server: powershell python server.py

  4. Connect from an MCP client (e.g., Claude Desktop, VS Code with MCP support).