Displaybuddy
About
An MCP (Model Context Protocol) server that lets AI agents control Mac monitors via DisplayBuddy — adjust brightness, contrast, volume, input source, apply presets, sync displays, and more.
Details
- Author
- biocross
- Downloads
- 146
- Categories
- Other
Jump to
- Get overview and detailed info of all displays
- Set brightness, contrast, volume, input, rotation
- List and activate saved presets with optional delay
- List and toggle automation schedules
- Enable/disable multi-display sync
- Full local operation – no data leaves your machine
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
DisplaybuddyCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Ensure you have macOS with DisplayBuddy installed and running, the DisplayBuddy CLI installed (DisplayBuddy > Settings > General > Install CLI Tool), and Node.js 18+. Add the server to your MCP client’s configuration (e.g., claude_desktop_config.json with "command": "npx", "args": ["-y", "displaybuddy-mcp"]). Then use natural language prompts to control your monitors.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"displaybuddy": {
"displaybuddy-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"displaybuddy-mcp",
"--client",
"claude"
]
}
}
}
}McpServers
{
"displaybuddy-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"displaybuddy-mcp",
"--client",
"claude"
]
}
}DisplayBuddy MCP Server
An MCP (Model Context Protocol) server that lets AI agents control Mac monitors via DisplayBuddy — adjust brightness, contrast, volume, input source, apply presets, sync displays, and more.
Works with Claude Desktop, Cursor, Windsurf, Cline, and any MCP-compatible client.
Prerequisites
1. macOS with DisplayBuddy installed and running
2. DisplayBuddy CLI installed: open DisplayBuddy > Settings > General > Install CLI Tool
3. Node.js 18+
Installation
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"displaybuddy": {
"command": "npx",
"args": ["-y", "displaybuddy-mcp"]
}
}
}
Cursor
Add to your MCP settings:
{
"mcpServers": {
"displaybuddy": {
"command": "npx",
"args": ["-y", "displaybuddy-mcp"]
}
}
}
Smithery
npx -y @smithery/cli install displaybuddy-mcp --client claude
Available Tools
| Tool | Description |
|------|-------------|
| displaybuddy_status | Quick overview of all displays (call this first) |
| displaybuddy_list | Full display details including UUID, type, capabilities |
| displaybuddy_get | Get properties of a specific display |
| displaybuddy_set | Set brightness, contrast, volume, input, rotation |
| displaybuddy_preset_list | List saved presets |
| displaybuddy_preset_activate | Activate a preset (with optional delay) |
| displaybuddy_schedule_list | List automation schedules |
| displaybuddy_schedule_toggle | Enable or disable a schedule |
| displaybuddy_sync | Check/enable/disable multi-display sync |
Example Prompts
Once connected, you can ask your AI assistant things like:
- "Dim all my monitors to 30%"
- "What displays are connected?"
- "Switch my Dell monitor to HDMI"
- "Activate my Night Mode preset"
- "Sync all displays to my main monitor"
- "Turn up the brightness on my external display"
- "Set up my coding environment — brightness 70, contrast 60"
How It Works
The MCP server wraps the displaybuddy CLI, which communicates with the running DisplayBuddy app via URL scheme. All operations are local — no data leaves your machine.
AI Agent → MCP Server → displaybuddy CLI → DisplayBuddy App → Your Monitors
Development
```bash
npm install
npm run build
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
