LocalMind
About
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.
Details
- Author
- timosur
- Downloads
- 371
- Categories
- AI, Knowledge Base
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
LocalMindCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"localmind": {
"localmind": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}
}
}McpServers
{
"localmind": {
"command": "python3",
"args": [
"-m",
"venv",
".venv"
]
}
}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.
Local Development
Create a .env file in the backend folder:
APP_CONFIG_FILE_PATH=config.yaml
AZURE_OPENAI_API_KEY=x
AZURE_OPENAI_DEPLOYMENT=x
AZURE_OPENAI_ENDPOINT=https://x.openai.azure.com
AZURE_OPENAI_API_VERSION=2024-07-01-preview
AZURE_OPENAI_CHAT_MODEL=gpt-4o
AZURE_OPENAI_EMBEDDINGS_MODEL=embedding
Create a config.yaml file in your backend folder:
server:
- name: [SERVER_NAME]
command: [SERVER_COMMAND]
args:
- [SERVER_ARGS]
[...]
To work on the frontend in browser with the python backend up and running:
./dev.sh frontend-dev
To run the Tauri App in development mode with the python backend:
./dev.sh app-dev
RAG MCP Server
If you would like to use or work on the RAG MCP Server, first create a .env file in the rag folder:
AZURE_OPENAI_API_KEY=x
AZURE_OPENAI_DEPLOYMENT=x
AZURE_OPENAI_ENDPOINT=https://x.openai.azure.com
AZURE_OPENAI_API_VERSION=2024-07-01-preview
AZURE_OPENAI_CHAT_MODEL=gpt-4o
AZURE_OPENAI_EMBEDDINGS_MODEL=embedding
Create venv and install dependecies:
cd rag
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Then add the following config entry to your config.yaml in your backend folder:
server:
- name: rag
command: [ABSOLUTE_PATH]/rag/.venv/bin/python3
args:
- [ABSOLUTE_PATH]/rag/main.py
Important
Currently only works with Azure OpenAI Service.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
