MCP server that gives AI assistants control over your Home Assistant. Including 50+ tools over 3 transports. Batteries included 🔋
Connect Home Assistant Model Context Protocol (MCP) to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server that gives AI assistants control over your Home Assistant. Including 50+ tools over 3 transports. Batteries included 🔋. The home assistant model context protocol (mcp) mcp server is what makes that connection.
You need a Home Assistant instance and a long-lived access token (create one here).
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
latest — Latest stable releasedev — Latest development build from main branchSpeech-to-Text — Fast, local transcription using faster-whisperSTDIO — for Claude Desktop, Cursor, VS Code (local editor integrations)Method — CommandCategory — ToolsLights — list, get, turn on/off, brightness, color temp, RGB, effectsClimate — list, get, HVAC modes, target temp, fan mode, humidifyMedia — list, get, play/pause, volume, source, sound mode, shuffleCovers — list, get, open/close, position, tilt, garage doorLocks — list, get, lock/unlock with code supportFans — list, get, speed, oscillation, direction, presetConfiguration is passed through the environment: HASS_HOST, HASS_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Home Assistant Model Context Protocol (MCP)'s toolset — latest, dev, Speech-to-Text and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jango-blockchained; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| latest | Latest stable release |
| dev | Latest development build from main branch |
| Speech-to-Text | Fast, local transcription using faster-whisper. |
| STDIO | for Claude Desktop, Cursor, VS Code (local editor integrations) |
| Method | Command |
| Category | Tools |
| Lights | list, get, turn on/off, brightness, color temp, RGB, effects |
| Climate | list, get, HVAC modes, target temp, fan mode, humidify |
| Media | list, get, play/pause, volume, source, sound mode, shuffle |
| Covers | list, get, open/close, position, tilt, garage door |
| Locks | list, get, lock/unlock with code support |
| Fans | list, get, speed, oscillation, direction, preset |
| Vacuums | list, get, start/stop/dock, spot clean, fan speed |
| Alarm | list, get, arm home/away/night, disarm |
{
"mcpServers": {
"advanced-homeassistant": {
"command": "npx",
"args": ["-y", "@smithery/cli"],
"env": {
"HASS_HOST": "your-value",
"HASS_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| HASS_HOST | Endpoint or connection string the server talks to. | Optional |
| HASS_TOKEN | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.