Home Assistant MCP Server

@jango-blockchained

代码仓库主页

基本信息

分类

AI 与智能体

许可证

Apache-2.0

传输方式

stdio

作者

jango-blockchained

关于 Home Assistant MCP Server

MCP server that gives AI assistants control over your Home Assistant. Including 50+ tools over 3 transports. Batteries included 🔋

#speech-recognition #home-assistant #speech-to-text #llm #mcp-server

Home Assistant MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "advanced-homeassistant-mcp": {
      "command": "npx",
      "args": [
        "@smithery/cli",
        "install",
        "@jango-blockchained/advanced-homeassistant-mcp",
        "--client",
        "claude"
      ]
    }
  }
}

Home Assistant MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Home Assistant Model Context Protocol (MCP)?

The Home Assistant Model Context Protocol (MCP) server connects AI assistants like Claude, GPT, Cursor, and Copilot to a Home Assistant instance. It provides over 50 tools to control smart home devices, support for three transport methods, and local voice control features, targeting both developers and smart home enthusiasts.

How to use Home Assistant Model Context Protocol (MCP)?

Install via bunx, npx, Docker, npm global, or Smithery. Configure with HASS_HOST and HASS_TOKEN environment variables. Use with Claude Desktop, Cursor, VS Code, or any MCP client. Start with one command: bunx github:jango-blockchained/advanced-homeassistant-mcp.

Key features of Home Assistant Model Context Protocol (MCP)

50+ tools for lights, climate, media, locks, and vacuums
Three transports: STDIO, HTTP+WS, and HTTP fastmcp
Supports Claude Desktop, Cursor, VS Code, and Smithery
Speech features with wake word and speech-to-text
Energy monitoring, maintenance, and automation management
Full-text entity search and history queries

Use cases of Home Assistant Model Context Protocol (MCP)

Voice-controlled smart home via AI assistants
Automate scenes, notifications, and device management
Monitor energy consumption and identify orphaned devices
Remotely control Home Assistant through chat interfaces
Debug automations with trace queries and error logs

常见问题

What do I need to run it?

A Home Assistant instance and a long-lived access token from your account profile.

How do I install it?

Use bunx, npx, Docker, npm global, or Smithery one‑click install. See the Quick Start section for details.

What transports are supported?

STDIO for local editor integrations (Claude Desktop, Cursor, VS Code) and HTTP+WS for remote AI hosts with JWT auth, plus HTTP via fastmcp.

Can I control voice?

Yes, with the speech features Docker Compose file, using wyoming‑openwakeword for wake word and faster‑whisper for speech‑to‑text.

Where does the data live?

All communication happens between the AI assistant and your Home Assistant instance; no external cloud storage is required.

AI 与智能体分类下的更多 MCP 服务器

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

Heterogent

Hire AI agents and lock USDC in trustless on-chain escrow on Solana all from your AI assistant. Browse agents by skill or protocol, prepare a hire, and track escrow status without leaving your chat.

superbot

EZO Labs

superbot is your own AI agent: anything you can do on your computer, it can do, fast. Its MCP server gives other agents one tool for errands: fax, calls, texts, Gmail drafts, calendar, web search. Free in your browser, n

q-ring

I4cTime

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.