mcpField
🤝
🤝

🤝

Local
github.com/miguelg719AI & Agents3Updated 96w ago
Repository

About 🤝

Home Assistant MCP Server connects to Home Assistant to control supported smart-home domains. It provides tools for lights, climate, locks, alarm panels, and humidifiers, along with prompts for each domain’s tools.

Key features

  1. 01Light power and brightness control
  2. 02Climate temperature and HVAC mode control
  3. 03Lock and unlock controls
  4. 04Alarm panel arm and disarm controls
  5. 05Humidifier controls
  6. 06Domain-specific prompts

Use cases

  1. 01Turn lights on or off and adjust brightness
  2. 02Change temperature or HVAC mode
  3. 03Operate locks and alarm panels
  4. 04Control a humidifier

MCP support

It exposes Home Assistant domain controls as tools to MCP clients and provides prompts for each domain’s tool set.

#home-assistant#mcp-server#smart-home

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

README image 🤝 README image Home Assistant MCP Server

A Model Context Protocol (MCP) server project that integrates with Home Assistant to provide smart home control capabilities.

Prompts

The server provides prompts for each domain's set of tools.

Tools

The server implements control for various Home Assistant domains. Currently supports:

  • 💡 Lights: Turn on/off, brightness control
  • 🌡️ Climate: Temperature control, HVAC modes
  • 🔒 Locks: Lock/unlock functionality
  • 🚨 Alarm Control Panel: Arm/disarm security systems
  • 💧 Humidifier: Humidity control

Example tools include:

light-turn_on()
climate-turn_off()
alarm_control_panel-disarm()
lock-lock()
humidifier-turn_off()

Configuration

Environment Variables

Create a .env file in the root directory with:

HOMEASSISTANT_TOKEN=your_long_lived_access_token_here # get it from your Home Assistant instance after onboarding
HOMEASSISTANT_BASE_URL=your_home_assistant_url_here # e.g. http://homeassistant.local:8123

Quickstart

Install

Follow the instructions on how to install Home Assistant and get a long lived access token.

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration ``` "mcpServers": { "home-assistant-server": { "command": "uv", "args": [ "--directory", "/path/to/home-assistant-server", "run", "home-assistant-server" ] } } ```
Published Servers Configuration ``` "mcpServers": { "home-assistant-server": { "command": "uvx", "args": [ "home-assistant-server" ] } } ```

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package distributions:
uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:
uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD
Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/miguel/Documents/home-assistant-server/home-assistant-server run home-assistant-server

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Contributing

Thanks for your interest in contributing to this project!

Please see CONTRIBUTING.md for guidelines.

License

MIT License - see LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.