mcp-desktop-automation
If you are the rightful owner of mcp-desktop-automation and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol server that provides desktop automation capabilities using RobotJS and screenshot capabilities.
The MCP Desktop Automation server is designed to enable LLMs to control desktop environments by simulating mouse movements, keyboard inputs, and capturing screenshots. It leverages RobotJS for automation tasks and provides a structured interface for interacting with desktop elements. The server is primarily tested with Claude Desktop and requires system-level permissions to function effectively. It supports various automation tasks, including screen size detection, mouse control, and keyboard input simulation. The server is built on Node.js and is distributed under the MIT License, allowing for modification and distribution.
Features
- Desktop mouse control
- Keyboard input simulation
- Screen size detection
- Screenshot capabilities
- Simple JSON response format
Tools
get_screen_size
Gets the screen dimensions. No input parameters required.
screen_capture
Captures the current screen content. No input parameters required.
keyboard_press
Presses a keyboard key or key combination. Inputs: key (string, required), modifiers (array of strings, optional).
keyboard_type
Types text at the current cursor position. Input: text (string, required).
mouse_click
Performs a mouse click. Inputs: button (string, optional), double (boolean, optional).
mouse_move
Moves the mouse to specified coordinates. Inputs: x (number, required), y (number, required).
