Home Assistant MCP

Name: Home Assistant MCP
Author: Community / homeassistant-ai

Control your smart home with natural language

Official

AI & ML

Install Command

npx -y ha-mcp-server

Claude Desktop Config

{
  "mcpServers": {
    "homeassistant": {
      "command": "npx",
      "args": ["-y", "ha-mcp-server"],
      "env": { "HA_URL": "http://homeassistant.local:8123", "HA_TOKEN": "<LONG_LIVED_TOKEN>" }
    }
  }
}

Home Assistant MCP is an officially maintained MCP server in the AI & ML category, developed by Community / homeassistant-ai. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.

About Home Assistant MCP

Home Assistant MCP server enables AI assistants to control and query your smart home devices.

Features

Control lights, switches, climate, locks
Query sensor states and history
Execute Home Assistant automations and scripts
Manage scenes
Access device and area information
Works with all Home Assistant integrations

Who Should Use Home Assistant MCP?

1Chain AI models and pipelines through a unified MCP interface
2Let Claude orchestrate other AI tools and models
3Integrate embeddings, image generation, or speech APIs into your workflow
4Build multi-model workflows without writing custom integration code

How to Install Home Assistant MCP

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.

How Home Assistant MCP Compares

✦It is an officially maintained server — unlike community alternatives, it is built and supported by the original project team, ensuring compatibility with upstream changes.

✦It runs entirely on your local machine, so no data leaves your environment — important for teams with privacy or compliance requirements.

✦Authentication uses API keys, giving you fine-grained control over access without requiring a full OAuth setup.