Home Assistant MCP

Home Assistant MCP

Expose all Home Assistant voice intents through a Model Context Protocol Server allowing home control.

allenporter

Home Automation & IoT
Speech Processing
Visit Server

README

mcp-server-home-assistant

A Model Context Protocol Server for Home Assistant. See Model Context Protocol for context.

The custom component required by this integration is moving to Home Assistant Core in https://github.com/home-assistant/core/pull/134122

Usage in Claude Desktop

  1. Install the home-assistant-model-context-protocol custom component in your Home Assistant instance

  2. Create a Long Lived Access Token

  3. Clone this git repo to a path like /Users/allen/Development/mcp-server-home-assistant

  4. Edit your claude_desktop_config.json with something like this and include your home assistant url and api token:

    {
    "mcpServers": {
        "Home-assistant": {
            "command": "uv",
            "args": [
                "--directory",
                "/Users/allen/Development/mcp-server-home-assistant",
                "run",
                "mcp-server-home-assistant",
                "-v",
                "-v"
            ],
            "env": {
                "HOME_ASSISTANT_WEB_SOCKET_URL": "http://localhost:8123/api/websocket",
                "HOME_ASSISTANT_API_TOKEN": "byJhbVci0iJIUzI1ii1sInR5cCI6IkpXVCJ9.....
            }
        }
    }
}

  5. You can view the logs e.g. ~Library/Logs/Claude/mcp-server-Home-assistant.log to understand what is happening

Recommended Servers

mcp-server-youtube-transcript

mcp-server-youtube-transcript

A Model Context Protocol server that enables retrieval of transcripts from YouTube videos. This server provides direct access to video captions and subtitles through a simple interface.

Featured
JavaScript
ThingsPanel MCP

ThingsPanel MCP

An integration server that connects AI models with ThingsPanel IoT platform, allowing AI assistants to interact with IoT devices through natural language for device control, data retrieval, and management operations.

Official
Python
Say MCP Server

Say MCP Server

Enables text-to-speech functionality on macOS using the say command, offering extensive control over speech parameters like voice, rate, volume, and pitch for a customizable auditory experience.

Local
JavaScript
Ollama MCP Server

Ollama MCP Server

Enables seamless integration between Ollama's local LLM models and MCP-compatible applications, supporting model management and chat interactions.

Local
TypeScript
mcp-hfspace

mcp-hfspace

Use HuggingFace Spaces directly from Claude. Use Open Source Image Generation, Chat, Vision tasks and more. Supports Image, Audio and text uploads/downloads.

Local
TypeScript
OpenHue MCP Server

OpenHue MCP Server

Enables control of Philips Hue lights through Claude and other LLM interfaces using the OpenHue CLI.

Local
TypeScript
Kokoro TTS MCP Server

Kokoro TTS MCP Server

Provides text-to-speech capabilities through the Model Context Protocol, allowing applications to easily integrate speech synthesis with customizable voices, adjustable speech speed, and cross-platform audio playback support.

Local
Python
Voice Recorder MCP Server

Voice Recorder MCP Server

Enables recording audio from a microphone and transcribing it using OpenAI's Whisper model. Works as both a standalone MCP server and a Goose AI agent extension.

Local
Python
Speech MCP

Speech MCP

A Goose MCP extension providing voice interaction with modern audio visualization, allowing users to communicate with Goose through speech rather than text.

Local
Python
MCP2Serial

MCP2Serial

A bridge that connects physical hardware devices with AI large language models via serial communication, allowing users to control hardware using natural language commands.

Local
Python