
Homey MCP Server
Enables interaction with Homey smart home devices through natural language, allowing users to control devices, manage zones, and trigger automation flows.
README
MCP Server for Homey
Model Context Protocol (MCP) server for interacting with the Homey smart home platform.
Features
- Device Management: List and control all Homey devices
- Capability Control: Set device capabilities (on/off, brightness, temperature, etc.)
- Zone Management: List and organize zones
- Flow Automation: List and trigger Homey Flows
Prerequisites
- Node.js >= 18
- A Homey Pro device with local API access
- Homey API token and local IP address
Getting Homey API Credentials
- Navigate to Settings → API Keys in the Homey Web App
- Tap "New API Key"
- Give it a name and select appropriate permissions
- Copy the generated API token
- Find your Homey's local IP address in Settings → General → Network
Installation
npm install
npm run build
Configuration
Create a .env
file or set environment variables:
HOMEY_API_TOKEN=your_api_token_here
HOMEY_LOCAL_IP=192.168.1.xxx
Usage
Running the Server
With Node.js
npm run build
node dist/index.js
With Docker
Build the Docker image:
docker build -t mcp-server-homey .
Run the container:
docker run -e HOMEY_API_TOKEN=your_api_token_here -e HOMEY_LOCAL_IP=192.168.1.xxx mcp-server-homey
Or use docker-compose (create a docker-compose.yml
):
version: '3.8'
services:
mcp-server-homey:
image: mcp-server-homey
build: .
environment:
- HOMEY_API_TOKEN=your_api_token_here
- HOMEY_LOCAL_IP=192.168.1.xxx
restart: unless-stopped
Then run:
docker-compose up -d
Claude Desktop Configuration
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"homey": {
"command": "node",
"args": ["/absolute/path/to/demo/dist/index.js"],
"env": {
"HOMEY_API_TOKEN": "your_api_token_here",
"HOMEY_LOCAL_IP": "192.168.1.xxx"
}
}
}
}
Available Tools
list_devices
List all devices connected to Homey with their capabilities and status.
get_device
Get detailed information about a specific device.
Parameters:
deviceId
(string): The ID of the device
set_capability
Set a capability value for a device.
Parameters:
deviceId
(string): The ID of the devicecapability
(string): The capability to set (e.g.,onoff
,dim
,target_temperature
)value
(any): The value to set
Examples:
- Turn on a light:
{ deviceId: "abc123", capability: "onoff", value: true }
- Set brightness:
{ deviceId: "abc123", capability: "dim", value: 0.5 }
- Set temperature:
{ deviceId: "abc123", capability: "target_temperature", value: 21 }
list_zones
List all zones in your Homey setup.
list_flows
List all available Flows.
trigger_flow
Trigger a specific Homey Flow.
Parameters:
flowId
(string): The ID of the flow to trigger
Development
Watch Mode
npm run watch
Lint
npm run lint
Fix Linting Errors
npm run lint:fix
Project Structure
.
├── src/
│ └── index.ts # Main MCP server implementation
├── dist/ # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.md
Common Device Capabilities
onoff
: Turn device on/off (boolean)dim
: Brightness level (0-1)target_temperature
: Target temperature (number)measure_temperature
: Current temperature (read-only)measure_power
: Power consumption (read-only)measure_humidity
: Humidity level (read-only)volume_set
: Volume level (0-1)speaker_playing
: Playback state (boolean)
Troubleshooting
Connection Issues
- Verify your Homey's local IP address hasn't changed
- Ensure the API token has sufficient permissions
- Check that your device is on the same network as Homey
Device Not Found
- Use
list_devices
to get the correct device ID - Verify the device is available in the Homey app
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.