Back to MCP Catalog

Home Assistant Integration MCP Server

Smart HomePython
Control and query your Home Assistant smart home with AI assistants
Available Tools

get_entity_state

Get the current state of a specific Home Assistant entity

entity_id

set_entity_state

Control a Home Assistant entity by changing its state

entity_idstateattributes

search_entities

Search for entities in Home Assistant by name, type, or state

querydomain

get_domain_summary

Get a summary of entities in a specific domain (like lights, switches, etc.)

domain

system_overview

Get a high-level overview of the Home Assistant system

get_automations

List all automations in the Home Assistant system

guided_conversation

Start a guided conversation for common Home Assistant tasks

task_type

Home Assistant Integration enables AI assistants like Claude to interact directly with your Home Assistant instance. This powerful integration allows you to query device states, control smart home entities, get system summaries, and troubleshoot automations through natural language conversations. With token-efficient responses and guided conversation flows, it makes managing your smart home through AI assistants seamless and intuitive.

Home Assistant Integration

This MCP server connects AI assistants like Claude to your Home Assistant smart home system, enabling natural language control and querying of your devices, automations, and sensors.

Features

  • Query the state of any device or sensor in your smart home
  • Control lights, switches, and other entities through natural language
  • Get comprehensive summaries of your smart home system
  • Troubleshoot automations and entity issues
  • Search for specific entities by name, type, or state
  • Use guided conversations for common smart home tasks

Installation Options

Docker Installation (Recommended)

  1. Make sure you have Docker installed on your system

  2. You'll need a Home Assistant long-lived access token:

    • In Home Assistant, go to your profile (click your username in the sidebar)
    • Scroll down to "Long-Lived Access Tokens"
    • Create a new token with a descriptive name like "AI Assistant"
    • Copy the token value (you won't be able to see it again)
  3. Configure your AI assistant to use the MCP server by adding the appropriate configuration to your settings.

Manual Installation

If you prefer not to use Docker:

  1. Ensure you have Python 3.13+ installed
  2. Install uv for package management
  3. Clone the repository: git clone https://github.com/voska/hass-mcp
  4. Navigate to the directory: cd hass-mcp
  5. Copy the example environment file: cp .env.example .env
  6. Edit the .env file to add your Home Assistant URL and token
  7. Install dependencies: uv pip install -e .
  8. Run the server: python -m app.main

Configuration

When setting up the MCP server, you'll need to provide:

  • HA_URL: The URL of your Home Assistant instance (e.g., http://homeassistant.local:8123)
  • HA_TOKEN: Your Home Assistant long-lived access token

If running Home Assistant on the same machine as the MCP server in Docker:

  • Use http://host.docker.internal:8123 for Mac/Windows
  • You may need to use --network host in Docker args or use your machine's IP address

Usage Examples

Once configured, you can ask your AI assistant questions like:

  • "What's the temperature in the living room?"
  • "Turn off all the lights in the kitchen"
  • "Is my front door locked?"
  • "Give me a summary of all my smart home devices"
  • "What automations do I have set up?"
  • "Help me troubleshoot why my motion sensor isn't working"

The MCP server handles translating these natural language requests into Home Assistant API calls and formatting the responses in a way that's both informative for you and token-efficient for the AI.

Related MCPs

Home Assistant Integration
Smart HomeTypeScript

Control and monitor your Home Assistant smart home devices through Claude

Home Assistant
Smart HomePython

Control and query your Home Assistant smart home system through natural language

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.