io.github.Coolver/home-assistant-mcp
编码与调试by coolver
可在 IDE 中以 Vibecode 方式配置 Home Assistant,涵盖自动化、仪表盘、主题与设置。
什么是 io.github.Coolver/home-assistant-mcp?
可在 IDE 中以 Vibecode 方式配置 Home Assistant,涵盖自动化、仪表盘、主题与设置。
README
Home Assistant Vibecode MCP
⚙️ This MCP server works together with the
Home Assistant Vibecode Agent,
installed as a Home Assistant add-on.
The agent runs on your Home Assistant instance and provides “eyes and hands” for AI IDEs like Cursor, VS Code, Claude Code, or any other MCP-enabled IDE.
Let AI build your Home Assistant automations – or act as your DevOps for the ones you write by hand. Just describe what you need in natural language. 🏠🤖
You describe your goal → AI inspects your Home Assistant → designs a custom solution → and deploys it on-board automatically. 🚀
And if you prefer to handcraft your automations and scripts yourself, the agent can simply act as your DevOps and extra pair of hands: quickly uploading your changes, running tests, and analyzing logs on demand. You stay in control and decide how much you delegate to AI and how deep it should go.
Transform the way you manage your smart home. This add-on enables Cursor, Visual Studio Code (VS Code), or any MCP-enabled IDE to:
- 📝 Analyze your Home Assistant configuration, entities, and devices
- 🏗️ Create intelligent automations, scripts, and complete systems — including Home Assistant helpers that can be fully managed programmatically
- 🎨 Design and customize Lovelace dashboards with full control over cards, layouts, and styling
- 🖌️ Create and tweak themes for a personalized UI
- 🔄 Safely deploy changes with automatic Git-based versioning
- 🔍 Monitor and troubleshoot your setup through log analysis
- 📦 Install and manage HACS integrations and custom repositories
No more manual YAML editing or searching through documentation - just describe what you want in natural language!
Example: "Install smart climate control for my radiators" → AI creates 10+ automations, helpers, sensors, and scripts optimized for YOUR TRVs.
Built on Model Context Protocol and powered by HA Vibecode Agent.
✨ Key Features
🔍 Analyze your setup
✅ Read your full configuration — entities, automations, scripts, helpers
✅ Understand your devices — capabilities, relations, and usage patterns
✅ Learn existing logic — analyze how your current automations and scripts behave
🏗️ Build intelligence
✅ Create complete systems — multiple interconnected automations in seconds
✅ Generate helpers and sensors — tailored to your actual setup and needs
✅ Write optimized scripts — based on real entities, areas, and devices
✅ Refactor existing logic — improve or merge automations instead of starting from scratch
📊 Dashboards & UI
✅ Create and update Lovelace dashboards — fully programmatically
✅ Add, remove, or rearrange cards — stat, graphs, history, custom cards, and more
✅ Control layouts and views — organize rooms, areas, and scenarios
✅ Design and tweak themes — colors, typography, and styles for a personalized UI
🔒 Safe operations
✅ Git-based versioning — every change is tracked with meaningful commit messages
✅ Human-readable commits — AI explains what changed and why
✅ Configuration validation — test before apply to reduce breaking changes
✅ One-click rollback — revert to a previous state if something goes wrong
✅ Activity log — full audit trail of what the agent did and when
📦 Extend with the community
✅ Install and configure HACS — unlock 1000+ community integrations
✅ Search repositories — themes, plugins, custom components, dashboards
✅ Install integrations — one-command setup for new HACS components
✅ Keep things fresh — update all HACS repositories from a single place
Result:
You describe your goal → AI inspects your Home Assistant → designs a custom solution → and deploys it on-board automatically. 🚀
🚀 How is this different from other MCP modules for Home Assistant?
Most MCP integrations I’ve seen for Cursor, VS Code or Claude work only on your local machine and talk to Home Assistant over SSH and sometimes the REST API.
For serious Home Assistant work, that’s not really enough:
Home Assistant is not just a bunch of YAML files. It exposes multiple internal APIs, and some of the most important ones are only available from inside HA itself over the WebSocket API.
When you access HA only via SSH, the AI usually has to generate and upload a helper script on every request, then execute it blindly on the host. Since that script can be different every time, each request is a bit of a black box — more like playing Russian roulette than doing reliable automation.
Because of that, I chose a different architecture.
This project is split into two modules:
Home Assistant Agent (this module) – runs inside Home Assistant (as an add-on), has native access to all relevant APIs, files and services, and exposes a safe, well-defined interface for external tools.
Home Assistant MCP server – runs on your computer alongside your AI IDE (Cursor, VS Code, etc.) and talks to the Agent over a controlled API instead of SSH hacks (installation steps below)
This design makes working with Home Assistant faster, more predictable, safer and repeatable. Your AI IDE gets exactly the actions and data it needs — through a stable API — instead of constantly inventing ad-hoc scripts and hoping they behave correctly.
📋 Prerequisites
Before installing, you need:
- Home Assistant running (any version)
- HA Vibecode Agent v2.2.0+ installed as add-on
- Agent Key from HA Vibecode Agent (auto-generated on first start)
- AI-enabled editor installed (Cursor, VS Code + GitHub Copilot, Claude Code etc)
🚀 Quick Start (5 minutes)
Step 0: Install Node.js (if not already installed)
The MCP server requires Node.js to run on your computer (where your AI editor is installed):
- Check if Node.js is already installed: open terminal and run
node --version - If not installed or version is below v20.0.0, download and install from nodejs.org (use the 24.x LTS build when possible)
- After installation, verify:
node --versionshould show v20.0.0 or higher (v24 LTS recommended) - Important: Install Node.js on the computer where your AI editor runs, not on the Home Assistant server
Step 1: Install HA Vibecode Agent
Install the agent in your Home Assistant from :
- Go to Settings → Add-ons → Add-on Store
- Click ⋮ → Repositories
- Add:
https://github.com/Coolver/home-assistant-vibecode-agent - Install HA Vibecode Agent (v2.0.0+)
- Start the agent
Step 2: Setup MCP in Your AI Editor
Get configuration from Home Assistant:
- Open your Home Assistant (usually http://homeassistant.local:8123)
- Go to Settings → Add-ons → HA Vibecode Agent
- Click "Open Web UI" button
- Click the Cursor or VS Code tab (depending on which IDE you want to use with Home Assistant) and follow the setup instructions. You’ll need to install and configure Cursor or VS Code so they can connect to the HA Agent via the MCP protocol.
- That’s it — you’re ready to start working with your Home Assistant scripts, automations and dashboards using AI. If you find this project useful and want to support its development, please consider giving it a GitHub Star ⭐
Step 3: Test Connection
Verify everything works:
Open your AI editor (Cursor, VS Code, etc) and send this message to AI:
Connect to my Home Assistant and show me:
1. List of all my climate entities
2. Current status of the HA Vibecode Agent
This will verify the MCP connection is working.
If AI successfully returns your entities and agent status, you're all set! ✅
Troubleshooting: If connection fails:
- Check that HA Vibecode Agent is running
- Ensure your AI editor was fully restarted
- Verify configuration was pasted correctly
Step 4: Start Building!
Just describe what you want in natural language - AI will handle the rest!
🔧 Configuration
Environment Variables
| Variable | Description | Required | Default |
|---|---|---|---|
HA_AGENT_URL | URL of HA Vibecode Agent | Yes | http://homeassistant.local:8099 |
HA_AGENT_KEY | Agent Key for authentication | Yes | - |
Custom Agent URL
If your agent runs on a different URL:
{
"mcpServers": {
"home-assistant": {
"command": "npx",
"args": ["-y", "@coolver/home-assistant-mcp@latest"],
"env": {
"HA_AGENT_URL": "http://<home-assistant-host>:8099",
"HA_AGENT_KEY": "your_api_key_here"
}
}
}
}
🐛 Troubleshooting
"Invalid Agent Key" error
- Check your Agent Key is correct in
mcp.json(underHA_AGENT_KEY) - Regenerate key if needed: Settings → Add-ons → HA Vibecode Agent → Open Web UI
- Make sure HA Vibecode Agent is running
- Verify agent is accessible:
curl http://homeassistant.local:8099/api/health
"Connection refused"
- Check HA Vibecode Agent is started in Home Assistant
- Verify the URL in
HA_AGENT_URL - Make sure port 8099 is not blocked by firewall
"spawn npx ENOENT" error
This error means Node.js is not installed or not found in your system PATH.
Solution: Install Node.js (v20.0.0 or higher; v24 LTS recommended) on the computer where Cursor is running:
- Download and install Node.js from https://nodejs.org
- Restart Cursor completely after installation
- Verify installation by running
node --versionin a terminal
Important: Node.js must be installed on your computer (where Cursor, VS Code, Claude or other IDE runs), not on the Home Assistant server.
🔐 Security
- ✅ All communication goes through HA Vibecode Agent (port 8099)
- ✅ Agent Key authentication for MCP clients
- ✅ Agent validates Agent Key for all requests
- ✅ Agent uses internal SUPERVISOR_TOKEN for Home Assistant API operations
- ✅ Your Agent Key is stored only in local IDE config file
- ⚠️ Never commit
mcp.jsonwith your Agent Key to git!
🤝 Related Projects
- HA Vibecode Agent - Home Assistant add-on (required)
- Model Context Protocol - Protocol specification
📝 License
MIT © Vladimir Eremeev
🔧 Development
Project Structure
home-assistant-mcp/
├── package.json # NPM package config
├── tsconfig.json # TypeScript config
├── src/
│ ├── index.ts # MCP server entry point
│ ├── ha-client.ts # HA Agent API client
│ ├── handlers.ts # Tool request handlers
│ ├── tools.ts # Legacy tool definitions
│ └── tools/ # Modular tool definitions
│ ├── index.ts # Tool exports
│ ├── files.ts # File operation tools
│ ├── system.ts # System operation tools
│ └── dashboard.ts # Dashboard tools
├── build/ # Compiled JavaScript output
├── README.md
├── CHANGELOG.md
└── QUICK_START.md
Architecture
MCP Server (index.ts) ← Communication Protocol
↓
Tool Handlers (handlers.ts) ← Business Logic
↓
HA Client (ha-client.ts) ← HTTP API Wrapper
↓
HA Vibecode Agent (https://github.com/Coolver/home-assistant-vibecode-agent) (REST API) ← Home Assistant Integration
🙏 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
💬 Support
- 🐛 Issues: GitHub Issues
- 💡 Discussions: GitHub Discussions
⭐ Show your support
Give a ⭐️ if this project helped you control your smart home with AI!
常见问题
io.github.Coolver/home-assistant-mcp 是什么?
可在 IDE 中以 Vibecode 方式配置 Home Assistant,涵盖自动化、仪表盘、主题与设置。
相关 Skills
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。