MCP.so
ログイン

Model Context Protocol Server for Home Assistant

@tevonsb

リポジトリ

Model Context Protocol Server for Home Assistant について

A MCP server for Home Assistant

基本情報

カテゴリ

AI とエージェント

ライセンス

Apache-2.0

ランタイム

node

トランスポート

stdio

公開者

tevonsb

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "homeassistant-mcp": {
      "command": "docker",
      "args": [
        "compose",
        "up",
        "-d"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Model Context Protocol Server for Home Assistant?

It is an MCP server that bridges a local Home Assistant instance with Language Learning Models (LLMs), enabling natural language control and monitoring of smart home devices. It provides a comprehensive API for device control, automation management, add-on management, and package management (HACS).

How to use Model Context Protocol Server for Home Assistant?

Install via Node.js (npm install, npm run build) or Docker Compose. Configure environment variables: HASS_HOST, HASS_TOKEN, HASS_SOCKET_URL, and server options. Run the server and connect an MCP client (e.g., Claude Desktop) by adding the server to the client config with the command node <path>/dist and environment variables.

Key features of Model Context Protocol Server for Home Assistant

  • Control lights, climate, covers, switches, sensors, media players, fans, locks, vacuums, cameras.
  • Real‑time updates via Server‑Sent Events (SSE).
  • Manage Home Assistant add‑ons (install, start, stop, restart).
  • Full integration with Home Assistant Community Store (HACS) packages.
  • Create, duplicate, enable/disable automations with complex triggers, conditions, actions.
  • Token‑based authentication and rate limiting; Docker support.

Use cases of Model Context Protocol Server for Home Assistant

  • Use natural language to turn on lights, adjust thermostats, or control media players.
  • Monitor real‑time device state changes and automation executions through SSE.
  • Automate routine tasks by creating or modifying automations programmatically.
  • Manage add‑ons and HACS packages from an LLM interface.

FAQ from Model Context Protocol Server for Home Assistant

What are the prerequisites?

Node.js 20.10.0+, npm, Docker Compose (optional), a running Home Assistant instance with a long‑lived access token, and optionally HACS and Supervisor for full features.

How do I configure the server?

Set environment variables in a .env file: HASS_HOST, HASS_TOKEN, HASS_SOCKET_URL, PORT, NODE_ENV, DEBUG. Use .env.example as a template.

Can I deploy with Docker?

Yes, Docker Compose is recommended. Clone the repo, copy .env.example to .env, edit the configuration, then run docker compose up -d. The server runs on port 3000.

What transports and authentication are supported?

The server uses HTTP endpoints with token‑based authentication (the HASS_TOKEN). Real‑time updates use SSE over HTTP. No other transports are mentioned.

Are there any known limits?

No limits are stated in the README. The server supports rate limiting and has extensive test coverage (95%).

コメント

「AI とエージェント」の他のコンテンツ

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

meGPT - upload an author's content into an LLM

adrianco

Code to process many kinds of content by an author into an MCP server

287

Web Agent Protocol

OTA-Tech-AI

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

500

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416