get_screen_sizeLABSCO SUMMARY
Real input on the real desktop, with a screenshot size ceiling to plan around.
get_screen_size followed by mouse_move gives an agent coordinates it can act on, and keyboard_type reaches applications that expose no API at all. Responses are capped at 1MB and a high-resolution screen_capture goes over that cap; the author names a modest display resolution as the one that works reliably, so lower the display or capture a smaller screen before a long session.
What it is
A desktop control server built on RobotJS. It reports the screen size, captures the screen, moves and clicks the mouse, and types text or presses key combinations at the current cursor.
What you get
- The screen dimensions, so coordinates can be worked out before anything moves
- A capture of the current screen, also readable afterwards through screenshot:// resources
- Mouse movement to an x, y coordinate
- Left, right or middle clicks, single or double
- Text typed at the current cursor position
- Single keys or combinations, holding control, shift, alt or command
Requirements
Node.js 14.x or newer, and operating-system permission to capture the screen and to control the mouse and keyboard — granted in your security settings the first time the client launches the server. Installs with npx mcp-desktop-automation.
Setup effort
One command — npx -y mcp-desktop-automation
USE CASES
01
Driving an application that has no API
Read the screen size, move to the coordinate you want and click, the same way a person would.
02
Filling in a desktop form
Type into the focused field, then tab or press enter to move on.
03
Showing the agent what is currently on screen
Capture the screen and let it read the result, rather than describing the window yourself.
04
Dismissing a dialog with a shortcut instead of a click
Press a key with control, shift, alt or command held, which is steadier than hunting for the button.
05
Working out where to click before clicking
Take the screen dimensions and a capture together, so the coordinate is derived from what is actually displayed.
6 tools
Listed in project docs. Your client may show a different list.
screen_capturekeyboard_presskeyboard_typemouse_clickmouse_moveBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Requires
- npx on PATH
- Node.js
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y mcp-desktop-automationMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"desktop-automation": {
"command": "npx",
"args": [
"-y",
"mcp-desktop-automation"
]
}
}
}
