IntelliGlow Smart Lighting MCP server for AI agents

IntelliGlow is an AI-powered smart lighting system that connects artificial intelligence assistants like Claude and ChatGPT to real smart bulbs through UDP network communication. It allows you to control your lighting using natural voice commands and AI reasoning, offering a smarter alternative to traditional smart lighting solutions.

Quick Installation

Prerequisites

Python 3.7+
A compatible smart bulb connected to your network

Installation Steps

# Core system installation
pip install -e .

# With voice capabilities (recommended)
pip install -e .[voice]

Configure Your Bulb (Optional)

By default, IntelliGlow connects to a bulb at IP address 192.168.1.45 on port 4000. You can override these settings:

export BULB_IP=192.168.1.45    # Your bulb's IP
export BULB_PORT=4000          # Your bulb's port

Running IntelliGlow

You have several options for running IntelliGlow:

# 1. MCP server only (for AI integration)
mcp-server-smartbulb

# 2. Voice interface only
mcp-server-smartbulb-voice

# 3. Complete IntelliGlow system (voice + AI + MCP)
python voice_enabled_server.py

Testing Connectivity

Test UDP communication with your smart bulb:

# Test communication with your bulb
python test_network_bulbs.py

Integrating with Claude Desktop

Add IntelliGlow to your Claude Desktop configuration by editing the claude_desktop_config.json file:

{
  "mcpServers": {
    "intelliglow": {
      "command": "python",
      "args": ["-m", "mcp_server_smartbulb.network_server"],
      "cwd": "/path/to/your/IntelliGlow",
      "env": {
        "BULB_IP": "192.168.1.45",
        "BULB_PORT": "4000"
      }
    }
  }
}

Using IntelliGlow

Voice Commands

IntelliGlow understands natural language commands such as:

"Turn on the lights"
"Set brightness to 75 percent"
"Make it blue"
"How are the lights?"
"Find smart bulbs"

MCP Tools for AI Integration

When integrated with AI assistants, the following functions are available:

discover_bulbs() - Find smart bulbs on the network
connect_to_bulb(ip, port) - Connect to a specific bulb
turn_on_bulb(ip, port) - Turn on a bulb
turn_off_bulb(ip, port) - Turn off a bulb
set_bulb_brightness(brightness, ip, port) - Set brightness (0-100)
set_bulb_color(color, ip, port) - Set color using hex codes
get_bulb_status(ip, port) - Get current bulb status
ping_bulb(ip, port) - Test connectivity to a bulb

Advanced Configuration

Custom Bulb Setup

Create a bulb_config.json file for more detailed configuration:

{
  "default_bulb": {
    "ip": "192.168.1.45",
    "port": 4000,
    "timeout": 5.0
  },
  "discovery": {
    "enabled": true,
    "timeout": 10.0,
    "port_range": {
      "start": 4000,
      "end": 4010
    }
  }
}

Troubleshooting

No Bulb Found

Ensure your smart bulb is on the same network
Check that the bulb is listening on port 4000

Try network discovery:

python -c "import asyncio; from mcp_server_smartbulb.bulb_discovery import BulbDiscovery; asyncio.run(BulbDiscovery().discover_bulbs())"

Voice Not Working

Install voice dependencies: pip install -e .[voice]
Check microphone permissions
Test with: python -m mcp_server_smartbulb.voice_interface

Connection Timeout

Check firewall settings
Verify bulb IP address
Increase timeout in bulb_config.json

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "intelliglow" '{"command":"python","args":["-m","mcp_server_smartbulb.network_server"],"env":{"BULB_IP":"192.168.1.45","BULB_PORT":"4000"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "intelliglow": {
            "command": "python",
            "args": [
                "-m",
                "mcp_server_smartbulb.network_server"
            ],
            "env": {
                "BULB_IP": "192.168.1.45",
                "BULB_PORT": "4000"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "intelliglow": {
            "command": "python",
            "args": [
                "-m",
                "mcp_server_smartbulb.network_server"
            ],
            "env": {
                "BULB_IP": "192.168.1.45",
                "BULB_PORT": "4000"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect