advanced-homeassistant-mcp
An advanced MCP server for Home Assistant. ๐ Batteries included.
Documentation
๐ Home Assistant MCP








> Talk to your house. Your AI assistant (Claude, GPT, Cursor, Copilot) โ connected to Home Assistant through the Model Context Protocol. 50+ tools, three transports, one `bunx` command.
# โก Fastest way to try it
bunx github:jango-blockchained/advanced-homeassistant-mcp๐ Quick Start
You need a Home Assistant instance and a long-lived access token (create one here).
Claude Desktop
Add to `claude_desktop_config.json`:
{
"mcpServers": {
"homeassistant-mcp": {
"command": "bunx",
"args": ["github:jango-blockchained/advanced-homeassistant-mcp"],
"env": {
"HASS_HOST": "http://your-ha-instance:8123",
"HASS_TOKEN": "your_long_lived_access_token"
}
}
}
}Restart Claude. You're done. Ask it to turn on the lights.
Cursor / VS Code
Cursor โ add to .cursor/mcp.json
{
"mcpServers": {
"homeassistant-mcp": {
"command": "bunx",
"args": ["github:jango-blockchained/advanced-homeassistant-mcp"],
"env": {
"HASS_HOST": "http://your-ha-instance:8123",
"HASS_TOKEN": "your_long_lived_access_token"
}
}
}
}VS Code + MCP Extension
Set your env vars in a `.env` file and use the pre-configured `.vscode/mcp.json`:
{
"mcp.servers": {
"homeassistant-mcp": {
"type": "stdio",
"command": "bun",
"args": ["run", "dist/stdio-server.mjs"],
"env": {
"HASS_HOST": "${env:HASS_HOST}",
"HASS_TOKEN": "${env:HASS_TOKEN}"
}
}
}
}Smithery (One-Click)
Install directly from the Smithery registry โ no config files needed:
npx @smithery/cli install @jango-blockchained/advanced-homeassistant-mcp --client claude๐ฆ All Install Options
| Method | Command |
|---|---|
| Smithery (easiest) | `npx @smithery/cli install @jango-blockchained/advanced-homeassistant-mcp --client claude` |
| bunx (no install) | `bunx github:jango-blockchained/advanced-homeassistant-mcp` |
| npx | `npx @jango-blockchained/homeassistant-mcp@latest` |
| Docker | `docker run -d -p 7123:7123 --env-file .env ghcr.io/jango-blockchained/advanced-homeassistant-mcp:1.7.0` |
| From source | `git clone ... && bun install && bun run build:all && bun run start:stdio` |
| npm global | `npm add -g @jango-blockchained/homeassistant-mcp && homeassistant-mcp` |
Available Docker tags:
- `latest` - Latest stable release
- `1.7.3`, `1.7`, `1` - Tagged versions
- `dev` - Latest development build from main branch
๐ฏ What You Can Do
Once connected, you talk to your house like you talk to a human:
"Turn off all lights in the bedroom"
"Set the thermostat to 72ยฐF"
"Lock all doors and start the vacuum"
"Show me energy consumption this week"
"What's the temperature in the living room?"
"Activate the movie scene"
"Notify everyone that dinner is ready"
"Check my Home Assistant health"
"Find orphaned devices with low battery"
"Analyze my light usage patterns"Every command maps to one of 50+ tools โ lights, climate, media, locks, covers, fans, vacuums, alarms, scenes, automations, notifications, history, energy monitoring, maintenance, and more.
Full tool reference (all 50+ tools)
| 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 |
| Switches | list, get, turn on/off/toggle |
| Scenes | list, activate named scene |
| Automations | list, toggle, trigger, create/edit/delete |
| Notifications | push alerts via HA channels |
| History | query historical states |
| Add-ons | install, configure, control |
| Packages | HACS integrations and custom components |
| Maintenance | orphaned devices, battery warnings, energy analysis |
| Smart Scenarios | nobody-home mode, window/heat conflicts, energy waste |
| Lighting | animations, scenarios, showcase, BPM/beat detection |
| Voice | wake word detection, speech-to-text, voice commands |
| Dashboard | query and manage Lovelace dashboards |
| Templates | render Jinja2 templates via HA |
| To-Do Lists | add, update, remove items |
| Traces | automation/script execution traces |
| Search | full-text entity search with filters |
| Entity State | get current state of any entity |
| Error Log | query HA error logs with filtering |
Full docs: Tools Reference
๐๏ธ Speech Features (Voice Control)
Transform your setup into a fully voice-controlled smart home assistant. The speech integration provides local, privacy-focused voice processing.
- Wake Word Detection: Powered by `wyoming-openwakeword` (default: "Hey Jarvis").
- Speech-to-Text: Fast, local transcription using `faster-whisper`.
- Audio Integration: Direct PulseAudio integration for seamless microphone access.
To enable speech features, use the dedicated Docker Compose file:
docker-compose -f docker-compose.speech.yml up -dSee the Speech Features Guide for detailed configuration and setup instructions.
๐งฑ Architecture
โโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโ
โ AI Assistant โโโโโโบโ Home Assistant โโโโโโบโ Your Smart Home โ
โ (Claude/GPT) โ โ MCP Server โ โ (Home Assistant)โ
โโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโ
โ โ
โโโโโโ โโโโโโ
โผ โผ
โโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโ
โ HTTP/WS โ โ STDIO โ
โ (Express) โ โ (fastmcp v3) โ
โโโโโโโโโโโโโโ โโโโโโโโโโโโโโโโThree transports, one codebase. Pick the one that fits your setup โ all expose the same 50+ tools.
- STDIO โ for Claude Desktop, Cursor, VS Code (local editor integrations)
- HTTP+WS โ for remote AI hosts, with JWT auth, rate limiting, and WebSocket streaming
- HTTP (fastmcp) โ lightweight HTTP transport without bespoke middleware
โ๏ธ Configuration
Minimal setup. Two variables are required:
HASS_HOST=http://homeassistant.local:8123
HASS_TOKEN=eyJ... # long-lived access tokenOptional:
PORT=7123 # HTTP server port (default: 4000)
LOG_LEVEL=info # debug | info | warn | error
JWT_SECRET=... # for HTTP/WS auth (min 32 chars)For the full list of 20+ environment variables, see the Configuration docs.
๐ ๏ธ Development
bun install # install dependencies
bun run build:all # build all three entry points
bun test # run test suite (80% coverage threshold)
bun run lint # ESLint + Prettier
bun run typecheck # TypeScript type checkingBuilt with Bun, TypeScript, and fastmcp. Three entry points:
- `dist/index.cjs` โ HTTP+WS on a custom Express-based MCP server
- `dist/stdio-server.mjs` โ STDIO via fastmcp v3
- `dist/http-server.mjs` โ HTTP via fastmcp v3
๐ Docs
Full documentation lives at **jango-blockchained.github.io/advanced-homeassistant-mcp** โ covers installation, configuration, all 50+ tools, deployment (HTTP, STDIO, Smithery), architecture deep-dives, and guides.
๐ค Contributing
PRs welcome. Keep it simple โ same code style, add tests, update docs if you touch public APIs.
1. Fork it
2. Branch it
3. Code it
4. Test it
5. PR it
See CONTRIBUTING.md for the full guidelines.
๐ License
MIT โ go build something cool.
Your smart home speaks MCP. Now your AI speaks it too. ๐ โก๐ค๐
> Batteries included. ๐
Frequently asked questions
What is advanced-homeassistant-mcp?
advanced-homeassistant-mcp is An advanced MCP server for Home Assistant. ๐ Batteries included.
How do I install advanced-homeassistant-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is advanced-homeassistant-mcp open source?
Yes โ it is hosted on GitHub at https://github.com/jango-blockchained/advanced-homeassistant-mcp and has 34 stars.
Related MCP tools
๐ค A visualization mcp contains 25+ visual charts using @antvis. Using for chart generation and data analysis. TypeScript-based implementation.
A Unified MCP Server Management App TypeScript-based implementation. Trusted by 800+ developers. Trusted by 800+ developers.
๐ Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, ...
Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling for the Model Context Protocol. Enhance AI assistants with powerf
๐ฆ Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Lan...
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP