Philips Hue MCP Service
Enables control of Philips Hue lights through the Model Context Protocol, providing tools for turning lights on/off, setting brightness and color, and retrieving light status.
README
Philips Hue MCP Service
A FastMCP service that provides tools and resources for controlling Philips Hue lights through the Model Context Protocol.
Installation
- Install dependencies:
pip install fastmcp qhue requests
Or install from the project directory:
pip install -e .
Setup
1. Find your Hue Bridge IP
- Open the Philips Hue app on your phone
- Go to Settings > My Hue System > [Your Bridge Name]
- Note the IP address
2. Create a Username/API Key
You need to create a username (API key) for your bridge:
- Press the physical button on your Hue bridge
- Within 30 seconds, run this Python script:
import requests
import json
bridge_ip = "192.168.1.123" # Replace with your bridge IP
response = requests.post(f"http://{bridge_ip}/api",
json={"devicetype": "hue_mcp_service#user"})
print(json.dumps(response.json(), indent=2))
- Save the returned username/API key
Usage
Running the Service
python hue_mcp_service.py
Available Tools
connect_to_bridge(bridge_ip, username)- Connect to your Hue bridgeturn_light_on(light_id)- Turn on a specific lightturn_light_off(light_id)- Turn off a specific lightset_light_brightness(light_id, brightness)- Set brightness (0-254)set_light_color(light_id, hue, saturation)- Set color using hue/saturation valuesset_light_xy_color(light_id, x, y)- Set color using CIE xy coordinates
Available Resources
lights- Get information about all lightslight/{light_id}- Get detailed information about a specific lightbridge-status- Get current bridge connection status
Example Usage
First, connect to your bridge:
connect_to_bridge("192.168.1.123", "your-username-here")
Then control your lights:
# Turn on light 1
turn_light_on("1")
# Set brightness to 50%
set_light_brightness("1", 127)
# Set to red color
set_light_color("1", 0, 254)
Color Values
Hue and Saturation
- Hue: 0-65535 (color wheel position)
- 0: Red
- 10922: Yellow
- 21845: Green
- 32768: Cyan
- 43690: Blue
- 54613: Magenta
- Saturation: 0-254 (color intensity, 0=white, 254=full color)
CIE xy Coordinates
- x, y: 0.0-1.0 (precise color specification in CIE color space)
- Common colors:
- Red: (0.675, 0.322)
- Green: (0.4091, 0.518)
- Blue: (0.167, 0.04)
- White: (0.3127, 0.329)
Requirements
- Python 3.8+
- FastMCP 2.0+
- qhue 2.0+
- requests 2.25+
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.