twinkly-mcp
Allows AI agents to control Twinkly smart lights, including turning them on/off, setting colors, changing brightness, and switching effects via natural language.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@twinkly-mcpTurn on the Christmas tree lights"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
twinkly-mcp
A Model Context Protocol (MCP) server that gives AI agents control of your Twinkly lights.
Point an MCP-capable assistant (Claude Desktop, Claude Code, etc.) at this server and ask it to turn your lights on, set a color, change brightness, or switch effects — in plain language.
It's built on top of the @twinklyjs/twinkly library, which talks to Twinkly devices over their local network API.
⚠️ Status: early development. The server is being built phase by phase — see CLAUDE.md for the implementation plan and progress. It is not yet usable.
What you'll be able to do
Ask your assistant things like:
"Turn the Christmas tree lights on / off"
"Make the lights warm white at 40% brightness"
"Set them to green"
"Switch to the sparkle effect"
"What are my lights doing right now?"
Related MCP server: lifx-mcp-server
Requirements
Node.js 20+
One or more Twinkly devices on the same local network
An MCP client (e.g. Claude Desktop or Claude Code)
Installation
Not published yet. Once available it will run via
npxwith no global install.
npx twinkly-mcpConfiguration
The server is configured via environment variables. The most common setup is a single device by IP:
Variable | Description |
| IP address of your Twinkly device (e.g. |
| JSON map of named devices, e.g. |
| Name of the device to use when a request doesn't specify one |
|
|
|
|
Don't know your device's IP? With discovery enabled, the server can find devices automatically, or you can ask the assistant to "discover my Twinkly devices".
Connecting an MCP client
Claude Desktop / Claude Code
Add the server to your MCP client configuration:
{
"mcpServers": {
"twinkly": {
"command": "npx",
"args": ["twinkly-mcp"],
"env": {
"TWINKLY_IP": "192.168.1.50"
}
}
}
}Restart the client, and the Twinkly tools will be available to the assistant.
How it works
AI assistant ──MCP──> twinkly-mcp ──local HTTP──> Twinkly device(s)The server translates natural-language requests into MCP tool calls, which it maps onto the Twinkly device API on your local network. Your device IPs and tokens stay local — nothing is sent to the cloud by this server.
Development
See CLAUDE.md for architecture, the configuration reference, and the phased build plan. Contributions and progress are tracked there.
License
ISC
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Appeared in Searches
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/paztek/twinkly-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server