HA Cursor Agent logo

HA Cursor Agent

Community
Coolver

Home Assistant MCP server agent. Enable Claude Code, Cursor, VS Code or any MCP-enabled IDE to help you vibe-code and manage Home Assistant: create and debug automations, design dashboards, tweak themes, modify configs, and deploy changes using natural language

PublisherCoolver
Repositoryhome-assistant-vibecode-agent
LanguagePython
Forks
52
Stars
632
Available tools
0
Transport typestdio
Categories
LicenseMIT
Links
  • Connect tools to AI workflows

    HA Cursor Agent exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    632 stars and 52 forks from the linked repository.

HA Vibecode Agent

Version License MCP Package Landing Page

Let AI build your Home Assistant automations โ€“ or act as your DevOps for the ones you write by hand. Just describe what you need in natural language. ๐Ÿ ๐Ÿค–

You describe your goal โ†’ AI inspects your Home Assistant โ†’ designs a custom solution โ†’ and deploys it on-board automatically. ๐Ÿš€

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 agent enables Claude Code, Cursor, Visual Studio Code (VS Code), or any MCP-enabled IDE to:

  • ๐Ÿ“ Analyze your Home Assistant configuration, entities, and devices
  • ๐Ÿ—๏ธ Create intelligent automations, scripts, and complete systems โ€” including Home Assistant helpers that can be fully managed programmatically
  • ๐ŸŽจ Design and customize UI dashboards with full control over cards, layouts, and styling
  • ๐Ÿ–Œ๏ธ Create and tweak themes for a personalized UI
  • ๐Ÿ”„ Safely deploy changes with automatic Git-based versioning
  • ๐Ÿ” Monitor and troubleshoot your setup through log analysis
  • ๐Ÿ“ฆ 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!

Real example: User says "Install smart climate control" โ†’ AI analyzes 7 TRVs, creates 10 automations + 9 helpers + 10 sensors + 5 scripts, deploys everything, and it just works!

https://github.com/user-attachments/assets/0df48019-06c0-48dd-82ad-c7fe0734ddb3

Full YouTube Demo:


๐ŸŽฏ What is this?

HA Vibecode Agent is a service that exposes a safe REST API and toolset, allowing AI assistants (Claude Code, Cursor, VS Code, Antigravity, and any MCP-enabled IDE) to safely work with your Home Assistant instead of just generating YAML in the dark.

It supports two deployment modes:

ModeFor whomHow it runs
Supervisor (Add-on)Home Assistant OS / SupervisedInstalled via HA Add-on Store (default)
Standalone (Docker)HA Container in Docker / Proxmox / NASRuns as a separate Docker container

Both modes provide the same core functionality. The only difference: Add-on management (install/uninstall/restart add-ons) requires the Supervisor and is not available in standalone mode.


๐Ÿš€ How is this different from other MCP modules for Home Assistant?

Home Assistant Agent + MCP Server

Most MCP integrations for Claude, Cursor, VS Code or Antigravity run only on your local machine and talk to Home Assistant over SSH, sometimes with the REST API.

For serious Home Assistant work, that is not enough.

Home Assistant is not just a set of YAML files. It exposes internal APIs, runtime state, entities, services and capabilities that are much easier and safer to access from inside Home Assistant itself.

SSH-based integrations often force the AI to generate and run temporary helper scripts on every request. Since those scripts can change every time, the result is hard to predict, hard to repeat and risky to rely on.

This project uses a different architecture.

Architecture

The project is split into two modules:

Home Assistant Agent

Runs inside, or alongside, Home Assistant.

It has native access to relevant APIs, files, entities, services and runtime state, and exposes a safe, well-defined interface for external tools.

Home Assistant MCP Server

Runs on your computer alongside your AI IDE, such as Cursor, VS Code, Claude Desktop or Antigravity.

It talks to the Agent over a controlled API instead of relying on SSH hacks.

Why this design

This makes Home Assistant automation faster, safer, more predictable and repeatable.

The AI IDE gets exactly the actions and data it needs through a stable API, instead of constantly inventing ad-hoc scripts.

It also improves context efficiency.

Instead of loading huge YAML files, full entity dumps, logs or generated scripts into the prompt, the Agent can return only the relevant context: selected entities, services, automation fragments, validation results, errors or structured summaries.

The result is less noise, fewer tokens, fewer wrong assumptions and more reliable edits.

In short

The MCP server gives your AI IDE a standard way to talk to Home Assistant.

The Agent gives it safe, native access to Home Assistant itself.

Together, they replace fragile SSH-based scripting with a stable, structured and context-efficient automation layer


โšก Installation (5 minutes)

Option A: Home Assistant Add-on (default, recommended)

For users running Home Assistant OS or Supervised installation.

This is the standard deployment โ€” the agent runs as a managed add-on inside Home Assistant with full access to Supervisor API.

1. Add Repository

Open your Home Assistant UI (usually http://homeassistant.local:8123):

  1. Go to Settings โ†’ Add-ons โ†’ Add-on Store โ†’ โ‹ฎ โ†’ Repositories (usually http://homeassistant.local:8123/hassio/dashboard )
  2. Add: https://github.com/coolver/home-assistant-vibecode-agent
  3. Click Add

2. Install and Start Add-on

Still in Home Assistant UI:

  1. Refresh the page
  2. Find HA Vibecode Agent โ†’ Click INSTALL
  3. Wait for installation to complete
  4. Enable โ†’ Start on boot: ON โ†’ and push START button
  5. Wait for startup (~10 seconds)
  6. Click "Open Web UI" button

You'll see this interface:

  1. 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.

  2. That's it โ€” 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 โญ

YouTube Installation guide: how to install the Home Assistant Cursor Agent


Option B: Standalone Docker (Proxmox / Docker / NAS)

For users running Home Assistant Container without Supervisor (e.g., in Proxmox LXC/VM, Synology NAS, or plain Docker Compose).

The agent runs as a separate Docker container alongside your Home Assistant instance and connects via a Long-Lived Access Token.

Prerequisites

  • Home Assistant running and accessible over the network
  • Long-Lived Access Token โ€” create one in HA UI: Profile (bottom-left) โ†’ Long-Lived Access Tokens โ†’ Create Token
  • Docker and Docker Compose installed on the host

1. Clone the repository

bash
git clone https://github.com/Coolver/home-assistant-vibecode-agent.git
cd home-assistant-vibecode-agent

2. Configure environment

bash
cp .env.example .env

Edit .env with your values:

env
HA_URL=http://192.168.1.100:8123
HA_TOKEN=your_long_lived_access_token_here
HA_CONFIG_PATH=/path/to/homeassistant/config

3. Start the agent

bash
docker compose -f docker-compose.standalone.yml up -d

4. Get the API key

The agent auto-generates an API key on first start. View it in the logs:

bash
docker compose -f docker-compose.standalone.yml logs | grep "API Key"

Or read it directly from the config directory:

bash
cat /path/to/homeassistant/config/.ha_cursor_agent_key

5. Configure your IDE

The agent is now available at http://<host-ip>:8099. Configure your MCP client (Cursor, VS Code, etc.) to connect using the API key from step 4.


๐Ÿค– Using with AI IDE (Cursor, VS Code etc)

This agent enables AI IDE to autonomously manage your Home Assistant through natural language - no manual copy-pasting needed!

โš ๏ธ Important Disclaimer

This tool is designed for experienced Home Assistant users who understand what they're doing.

  • โœ… Always review changes before applying them to production systems
  • โš ๏ธ AI can accidentally break your configuration if given incorrect instructions or outdated information
  • ๐Ÿ’พ Git versioning is enabled by default - all changes are backed up and can be rolled back
  • ๐Ÿ”„ Test in a safe environment first if you're new to AI-driven automation
  • ๐Ÿ“– Verify syntax and compatibility with your Home Assistant version

Use at your own risk. The automatic backup system minimizes risk but doesn't eliminate it.

Start Using

Once connected, just describe what you want in natural language:

Show me all my climate entities and their current states
Analyze my automations and suggest optimizations
Create a smart lighting automation for movie mode

AI will autonomously read your configuration, create components, and deploy everything automatically!

That's it! AI IDE will use the MCP protocol to communicate with your Home Assistant.

Learn more: MCP Home Assistant on GitHub | NPM Package

Real-World Examples

Build Smart Climate Control:

Install a smart climate control system for my TRV radiators. 
Analyze my current devices, create automations for efficient heating 
with predictive shutdown, buffer radiators, and adaptive cooldowns.
Set up monitoring sensors and dashboard.

AI will autonomously:

  • Detect all your TRV entities by analyzing Home Assistant
  • Create 10+ automations for intelligent heating control
  • Add 9 input helpers for system state management
  • Generate 10 template sensors for monitoring
  • Create 5 scripts for boiler and buffer control
  • Build Lovelace dashboard with all metrics
  • Test and deploy everything
  • All tailored to YOUR specific TRVs and configuration!

Optimize Existing System:

My heating wastes energy. Analyze my current climate automations 
and optimize for efficiency while maintaining comfort.

Debug Issues:

My bedroom lights automation isn't working. Check the logs, 
find the problem, and fix it.

Stop writing YAML manually! Just describe what you want. ๐Ÿš€


๐Ÿ“š API Documentation

For complete API documentation, authentication details, and usage examples, see DEVELOPMENT.md.

Quick access:

  • Swagger UI: http://homeassistant.local:8099/docs (when installed)
  • ReDoc: http://homeassistant.local:8099/redoc (when installed)

๐Ÿ” Monitoring

Check Agent Health

bash
# No auth required for health check
curl http://homeassistant.local:8099/api/health

Example response:

json
{
  "status": "healthy",
  "version": "2.0.1"
}

View Agent Logs

bash
curl -H "Authorization: Bearer YOUR_AGENT_KEY" \
     http://homeassistant.local:8099/api/logs/?limit=50

View Backup History

bash
curl -H "Authorization: Bearer YOUR_AGENT_KEY" \
     http://homeassistant.local:8099/api/backup/history

๐Ÿ›ก๏ธ Security

Safety Features

  • โœ… Path validation - Cannot access files outside /config
  • โœ… Authentication required - All endpoints (except health) require token
  • โœ… Automatic backups - Git commits before modifications with meaningful commit messages
  • โœ… Rollback capability - Restore any previous state
  • โœ… Configuration validation - Check before applying
  • โœ… Audit logs - Track all operations

Best Practices

  1. Always backup before major changes
  2. Check config before reloading
  3. Review logs after operations
  4. Use rollback if something breaks
  5. Test in dev environment first

๐Ÿ”ง Development

For development setup, project structure, API documentation, and local development instructions, see DEVELOPMENT.md.

๐Ÿค Contributing

Contributions are welcome! If you'd like to contribute:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

For detailed contribution guidelines, see CONTRIBUTING.md.


๐Ÿ› Troubleshooting

"spawn npx ENOENT" error (Claude Code / Cursor / VS Code / Other IDE Console)

This error means Node.js is not installed or not found in your system PATH.

Solution: Install Node.js (v20.0.0 or higher; Node.js 24 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 --version in a terminal Important: Node.js must be installed on your computer (where Cursor runs), not on the Home Assistant server.

Add-on won't start

Check logs: Supervisor โ†’ HA Vibecode Agent โ†’ Logs

Common issues:

  • Port 8099 already in use
  • Invalid configuration
  • Missing permissions

Standalone container won't start

Check logs: docker compose -f docker-compose.standalone.yml logs

Common issues:

  • HA_URL not set or unreachable
  • HA_TOKEN invalid or expired โ€” regenerate in HA UI โ†’ Profile โ†’ Long-Lived Access Tokens
  • Config volume not mounted correctly โ€” verify HA_CONFIG_PATH in .env

API returns 401 Unauthorized

  • Check Agent Key is correct
  • Regenerate key if needed: Settings โ†’ Add-ons โ†’ HA Vibecode Agent โ†’ Open Web UI (add-on mode), or read from /config/.ha_cursor_agent_key (standalone mode)
  • Ensure Authorization header is present
  • Format: Authorization: Bearer YOUR_AGENT_KEY

File operations fail

  • Check file paths are relative to /config
  • Ensure files exist for read/delete operations
  • Check YAML syntax for parse errors

Git versioning not working

  • Git versioning is always enabled in shadow repository (/config/ha_vibecode_git)
  • Check git_versioning_auto setting for auto/manual commit mode
  • View logs for Git errors
  • Ensure /config is writable

๐Ÿ’ฌ Support


๐Ÿ“œ License

MIT License - See LICENSE file


Ready to give your AI full control of Home Assistant? Install now! ๐Ÿš€

Installation

TypingMind
{
  "mcpServers": {
    "home-assistant-vibecode-agent": {
      "command": "npx",
      "args": [
        "-y",
        "@coolver/home-assistant-mcp@latest"
      ],
      "env": {
        "HA_AGENT_URL": "<HA_AGENT_URL>",
        "HA_AGENT_KEY": "<HA_AGENT_KEY>"
      }
    }
  }
}

Use HA Cursor Agent MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once HA Cursor Agent is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add HA Cursor Agent as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the HA Cursor Agent MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "home-assistant-vibecode-agent": {
      "command": "npx",
      "args": [
        "-y",
        "<mcp-server-package>"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the HA Cursor Agent MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the HA Cursor Agent MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use HA Cursor Agent to help me with this task?
HA Cursor Agent
Sure. I read it.
Here is what I found using HA Cursor Agent.

Frequently asked questions

What is the HA Cursor Agent MCP server used for?

HA Cursor Agent is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use HA Cursor Agent MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use HA Cursor Agent with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use HA Cursor Agent MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With HA Cursor Agent connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect HA Cursor Agent MCP to TypingMind?

HA Cursor Agent runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does HA Cursor Agent MCP provide in TypingMind?

HA Cursor Agent exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use HA Cursor Agent MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If HA Cursor Agent requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter ๐Ÿ‘‡