homeassistant-ai/ha-mcp

The Unofficial and Awesome Home Assistant MCP Server

What it solves

It allows AI assistants (like Claude or ChatGPT) to directly interact with a Home Assistant smart home setup. Instead of manually configuring devices and automations, users can use natural language to control their home, query device states, and manage the underlying system configuration.

How it works

The project implements a Model Context Protocol (MCP) server. This server acts as a bridge between an AI client and the Home Assistant API. It provides a comprehensive set of tools (87 in total) that the AI can call to perform actions such as executing services, reading entity states, editing YAML configurations, and managing dashboards.

Who it’s for

Smart home enthusiasts and Home Assistant users who want to integrate their AI assistants into their home automation ecosystem for easier control and control and configuration.

Highlights

  • Extensive Toolset: Provides 87 tools covering search, device control, automation management, and system administration.
  • Multiple Deployment Options: Can be installed as a Home Assistant custom component (via HACS), a Home Assistant app/add-on, a Docker container, or a standalone Python package.
  • Natural Language Configuration: Enables AI to create automations, scripts, and dashboard cards using plain text commands.
  • Safety Features: Includes a "Read Only Mode" toggle, tool-specific enable/disable settings, and automatic backups for edits.
  • Remote Access: Supports various remote connectivity methods including Nabu Casa, webhooks, and OIDC authentication.

Related

  • Project
    voska/hass-mcp

    An MCP server that integrates Home Assistant with LLMs, allowing AI assistants to control devices, manage dashboards, and troubleshoot automations via natural language.

  • Project
    Coolver/home-assistant-vibecode-agent

    A service that lets AI assistants like Claude Code and Cursor safely manage Home Assistant through natural language, with automatic versioning and rollback. It replaces fragile SSH-based scripting with a stable, structured API layer.

  • Project
    MAA-AI/MaaMCP

    An MCP server that enables AI assistants to automate Android devices and Windows desktop applications using OCR and background control.

  • Project
    wonderwhy-er/DesktopCommanderMCP

    Desktop Commander is an MCP server that enables AI assistants to perform local file management, execute terminal commands, and handle data analysis directly on your computer.

  • Project
    CursorTouch/Windows-MCP

    Windows‑MCP is an open‑source MCP server that exposes Windows UI‑automation tools (mouse, keyboard, window management, screenshots, browser DOM mode, etc.) to any LLM‑based AI agent. Installable via PyPI, it runs on Windows 10/11 with Python 3.14+, supports local `stdio` or network transports (SSE/HTTP), and includes optional auth, TLS, IP allow‑lists, and OAuth for secure remote access.