macOS Desktop Control
Supports UIby d-wwei
Native macOS desktop automation with screenshot, mouse, keyboard, and window management for AI agents.
What it does
Connects AI agents directly to the macOS desktop, allowing them to see the screen and interact with the OS via native automation tools. It provides a bridge for AI to operate the computer in both foreground and background modes.
Tools
screenshot: Captures screen, regions, or specific windows with smart compression.click: Performs mouse actions (left/right/double/triple) and drags.type_text: Sends keyboard input via multiple modes including IME bypass.key_press: Executes specific keyboard combinations via AppleScript.open_app: Launches macOS applications.list_windows: Enumerates open windows with IDs and PIDs for targeting.sim_tap/sim_type: Controls iOS simulators via xcrun simctl.emu_tap/emu_type: Controls Android emulators via adb.
Installation
Add to your claude_desktop_config.json:
{
"mcpServers": {
"macos-desktop-control": {
"command": "node",
"args": ["/path/to/macos-desktop-control/src/index.js"]
}
}
}
Supported hosts
Claude Desktop, Claude Code, Codex CLI, Gemini CLI, Cursor.
Quick install
npm install macos-desktop-controlInformation
- Pricing
- free
- Published
- 7/24/2026
- stars
- 0
Categories
Choose your AI client and follow the steps below.
Codex
Add to .codex/mcp.json: {"mcpServers": {"macos-desktop-control": {"command": "node", "args": ["/path/to/macos-desktop-control/src/index.js"]}}}Cursor
Add to .cursor/mcp.json: {"mcpServers": {"macos-desktop-control": {"command": "node", "args": ["/path/to/macos-desktop-control/src/index.js"]}}}Gemini CLI
Add to ~/.gemini/settings.json: {"mcpServers": {"macos-desktop-control": {"command": "node", "args": ["/path/to/macos-desktop-control/src/index.js"]}}}Claude Desktop
{
"mcpServers": {
"macos-desktop-control": {
"command": "node",
"args": ["/path/to/macos-desktop-control/src/index.js"]
}
}
}Related Apps
FinanceToolkit
MCP ServerProfessional-grade financial analysis toolkit for equities, options, and risk management.
DiffSitter MCP
MCP ServerAI-powered structural code navigation using tree-sitter ASTs for semantic understanding across 14+ languages.
OpenAI Apps SDK Examples
MCP AppOfficial example gallery of interactive MCP widgets for ChatGPT — 3D viewers, maps, carousels, shopping carts, and more.
Human MCP
MCP ServerGive AI agents human-like senses: visual analysis, image/video generation, speech synthesis, browser automation, and advanced reasoning — 29 MCP tools in one se
Containarium
MCP ServerSelf-hostable agent runtime with SSH-native isolation, eBPF egress policy, and MCP-native CLI.
Shopify MCP Server
MCP ServerDirect interaction with Shopify store data via GraphQL API for managing products, customers, and orders.
Git MCP Server
MCP ServerFull-featured Git MCP server exposing 28 tools for AI agents to clone, commit, branch, diff, merge, rebase, and more via STDIO or Streamable HTTP.
CodexPotter
MCP ServerAutonomous reconciliation loop that drives Codex to align your codebase with instructed states.