MCP.so
Sign In

LocalMind

@timosur

Repository

About LocalMind

LocalMind is an local LLM Chat App fully compatible with the Model Context Protocol. It uses Azure OpenAI as a LLM backend and you can connect it to all MCP Servers out there.

#mcp#rag#llm#mcp-server

Basic information

Category

AI & Agents

Transports

stdio

Publisher

timosur

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "localmind": {
      "command": "python3",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is LocalMind?

LocalMind is a local LLM Chat App fully compatible with the Model Context Protocol (MCP). It uses Azure OpenAI as the LLM backend and allows users to connect to any MCP server. It is intended for developers who want to run a local chat interface that integrates with various MCP-compatible services.

How to use LocalMind?

To use LocalMind, create a .env file in the backend folder with Azure OpenAI credentials and a config.yaml file specifying MCP server definitions. For frontend development, run ./dev.sh frontend-dev; for the Tauri app, run ./dev.sh app-dev. An optional RAG MCP server can be set up by creating a venv in the rag folder and adding its config to config.yaml.

Key features of LocalMind

  • Local LLM chat app with MCP protocol support
  • Uses Azure OpenAI as the LLM backend
  • Includes an optional RAG (Retrieval-Augmented Generation) MCP Server
  • Development scripts for frontend and Tauri app
  • Configurable MCP server connections via YAML file

Use cases of LocalMind

  • Running a local chat interface that connects to multiple MCP servers.
  • Developing and testing MCP server integrations with a local LLM.
  • Experimenting with RAG workflows using Azure OpenAI embeddings and chat models.
  • Building and debugging a Tauri-based desktop app with an MCP backend.

FAQ from LocalMind

What dependencies does LocalMind require?

LocalMind requires Python (with venv and pip), Node.js (for frontend), and an Azure OpenAI subscription with API key, endpoint, deployment, and version configured in .env.

How do I configure MCP servers in LocalMind?

MCP servers are defined in a config.yaml file in the backend folder, specifying the server name, command, and arguments.

Does LocalMind support the RAG functionality?

Yes, LocalMind includes an optional RAG MCP Server that can be set up by creating a Python virtual environment in the rag folder and adding its configuration to config.yaml. It uses Azure OpenAI for embeddings and chat.

Where does the conversation data live?

The README does not specify data persistence details. —

Comments

More AI & Agents MCP servers

Gemini MCP Server

aliargun

MCP server implementation for Google's Gemini API

259

mcp-hfspace MCP Server 🤗

evalstate

MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

387

LinkedIn MCP Server

stickerdaniel

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.

2.7K

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K

MCP-LLM Bridge

patruff

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

976