Desktop Automation MCP server

This MCP Desktop Automation server provides desktop automation capabilities using RobotJS and screenshot functionality. It enables language models to control mouse movements, keyboard inputs, and capture screenshots, making it possible for AI systems to interact with your desktop environment.

Installation Requirements

• Node.js (version 14.x or higher)

Configuration

To configure Claude Desktop to use the MCP Desktop Automation server, add the following configuration:

{
  "mcpServers": {
    "desktop-automation": {
      "command": "npx",
      "args": ["-y", "mcp-desktop-automation"]
    }
  }
}

Required Permissions

This server needs system-level permissions to function properly:

• Screen capture access
• Mouse control
• Keyboard input simulation

You may need to grant these permissions in your operating system's security settings when first running Claude Desktop with this server.

Available Tools

Screen Management

Get Screen Size

Retrieves the dimensions of your screen.

• No input parameters required

Screen Capture

Takes a screenshot of your current screen.

• No input parameters required
• Note: There is a 1MB response size limit. High-resolution screenshots may exceed this limit, so 800x600 resolution is recommended for reliable operation.

Keyboard Control

Keyboard Press

Presses a specific keyboard key or key combination.

• Inputs:
  • key (string, required): Key to press (e.g., 'enter', 'a', 'control')
  • modifiers (array of strings, optional): Modifier keys to hold while pressing the key. Possible values: "control", "shift", "alt", "command"

Keyboard Type

Types text at the current cursor position.

• Input:
  • text (string, required): Text to type

Mouse Control

Mouse Click

Performs a mouse click at the current position.

• Inputs:
  • button (string, optional, default: "left"): Mouse button to click. Possible values: "left", "right", "middle"
  • double (boolean, optional, default: false): Whether to perform a double click

Mouse Move

Moves the mouse cursor to specified coordinates.

• Inputs:
  • x (number, required): X coordinate
  • y (number, required): Y coordinate

Accessing Screenshots

The server provides access to captured screenshots:

Screenshot List

Access via screenshot://list to see all available screenshots by name.

Screenshot Content

Access via screenshot://{id} to retrieve PNG images of captured screenshots, where {id} is the timestamp-based name of the screenshot.

Limitations

• Primary testing has been done with Claude Desktop, though the server works with other MCP clients
• 1MB response size limit affects high-resolution screenshots
• For reliable operation, use 800x600 resolution or capture specific screen areas

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.