Zero-dependency macOS desktop automation for AI agents. 18 tools via MCP. macOS 13+.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

[!WARNING] This tool has full control over mouse, keyboard, and screen. Please use in a sandboxed environment to protect your privacy and avoid accidental data loss by your agents. You are responsible for any actions performed through this tool.
Zero-native-dependency macOS desktop automation via MCP.
Give AI agents eyes and hands on macOS β click, type, screenshot, and inspect any application.
get_ui_elements, validate screen content via screenshotopen_application, fill forms with type_text, navigate menus via click_menuscreenshot for visual diffing or alertingget_ui_elements for QA and compliance checksscreenshot, click, type_text, and morenpx mac-use-mcp and grant two macOS permissions. No node-gyp, no Xcode tools, no build step.Requirements: macOS 13+ and Node.js 22+. The server communicates over stdio transport.
This package only works on macOS. It will refuse to install on other operating systems.
No build steps. No native dependencies. Just run:
npxwill prompt to install the package on first run. Usenpx -y mac-use-mcpto skip the confirmation.
[!TIP] Model selection matters. Desktop automation involves screenshotβaction loops that add up in token usage. A fast model with solid reasoning, good vision, and reliable tool calling is recommended:
Model Provider Gemini 3 Flash Claude Sonnet 4.6 Anthropic GPT-5 mini OpenAI MiniMax-M2.5 MiniMax Kimi K2.5 Moonshot AI Qwen3.5 Alibaba GLM-4.7 Zhipu AI
mac-use-mcp requires two macOS permissions to function. Grant them once and you're set.
Required for mouse and keyboard control.
Required for screenshots.
After granting both permissions and configuring your MCP client (see next section), use the check_permissions tool to confirm everything is working:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
Add to ~/.codex/config.toml:
Or via CLI:
Add to ~/.gemini/antigravity/mcp_config.json:
Add to ~/.gemini/settings.json:
Add to .vscode/mcp.json in your workspace (or open the Command Palette and run MCP: Open User Configuration for global setup):
Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-level):
Add to ~/.codeium/windsurf/mcp_config.json:
Open Cline's MCP settings (in the Cline extension panel, click the MCP servers icon), then add:
Add to ~/.aws/amazonq/mcp.json:
This Node.js MCP server exposes 18 tools for mouse, keyboard, and screen control to any MCP-compatible client.
| Tool | Description |
|---|---|
screenshot | Capture the screen, a region, or a window by title (PNG or JPEG) |
get_screen_info | Get display count, resolution, origin, and scale factor for each display |
get_cursor_position | Get current cursor coordinates |
| Tool | Description |
|---|---|
click | Click at screen coordinates with button, click count, and modifier options |
move_mouse | Move the cursor to a position |
scroll | Scroll up, down, left, or right at a position |
drag | Drag from one point to another over a configurable duration |
type_text | Type text at the cursor position (supports Unicode, CJK, and emoji) |
press_key | Press a key or key combination (e.g., "cmd+c", "Return") |
| Tool | Description |
|---|---|
list_windows | List all visible windows with positions and sizes |
focus_window | Activate an app and bring a specific window to the front |
open_application | Launch an application by name |
click_menu | Click a menu bar item by path (e.g., "File > Save As...") |
App names support fuzzy matching β "chrome" resolves to "Google Chrome", "code" to "Code", etc.
| Tool | Description |
|---|---|
get_ui_elements | Query UI elements via Accessibility API β find buttons, text fields, and other controls by role or title |
| Tool | Description |
|---|---|
clipboard_read | Read the current system clipboard as plain text |
clipboard_write | Write text to the system clipboard |
| Tool | Description |
|---|---|
wait | Pause for a specified duration (in milliseconds, 0β10 000, default 500) |
check_permissions | Verify Accessibility and Screen Recording access |
Common workflow patterns using mac-use-mcp tools:
key code), window focus, and menu clicksSystem Events key code) as a workaround, which may behave differently in some edge cases.Grant Accessibility and Screen Recording permissions to your terminal app in System Settings > Privacy & Security. A restart of the terminal may be required.
macOS 15 (Sequoia) introduced stricter permission prompts. Allow the prompts when they appear. The check_permissions tool can verify your current permission status.
Some password fields and secure text inputs block programmatic key events. This is a macOS security feature. Use clipboard_write + press_key("cmd+v") as a workaround.
Ensure Screen Recording permission is granted to your terminal app (not just Accessibility). Restart the terminal after granting.
See CONTRIBUTING.md for development setup and guidelines.
To report a vulnerability, see SECURITY.md.
MIT Β© 2026 antbotlab
macOS is a trademark of Apple Inc., registered in the U.S. and other countries and regions.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/mac-use-mcp)<a href="https://allmcps.com/mcp/mac-use-mcp"><img src="https://allmcps.com/api/badge/mac-use-mcp?style=directory" alt="Mac Use Mcp on AllMCPs" /></a>