Wraps the DisplayBuddy CLI to give Claude control over your Mac's external monitors without leaving the keyboard. Exposes tools for adjusting brightness, contrast, volume, and input source across connected displays, plus activating saved presets and toggling automation schedules. You can sync settings across multiple monitors or target specific displays by UUID. Everything runs locally through DisplayBuddy's URL scheme, so you need the app installed and its CLI tool set up first. Useful when you're already chatting with Claude about your workflow and want to adjust your display setup without breaking focus to hunt for hardware buttons or menu bar controls.
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.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"displaybuddy": {
"command": "npx",
"args": ["-y", "displaybuddy-mcp"]
}
}
}
Add to your MCP settings:
{
"mcpServers": {
"displaybuddy": {
"command": "npx",
"args": ["-y", "displaybuddy-mcp"]
}
}
}
npx -y @smithery/cli install displaybuddy-mcp --client claude
| 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 |
Once connected, you can ask your AI assistant things like:
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
npm install
npm run build
# Test with MCP Inspector
npx -y @modelcontextprotocol/inspector node ./build/index.js
MIT