Swift MCP GUI Server
A Model Context Protocol (MCP) server that allows controlling macOS through SwiftAutoGUI. This server provides tools for programmatically controlling the mouse and keyboard through MCP clients.
Requirements
- macOS 15.0 or later
- Swift 6.0 or later
- Xcode 16.0 or later
Installation
- Clone this repository:
git clone https://github.com/NakaokaRei/swift-mcp-gui.git
cd swift-mcp-gui
- Install
swift package experimental-install
- Add command to your MCP client.
{
"mcpServers" : {
"swift-mcp-gui" : {
"command" : "/Users/USERNAME/.swiftpm/bin/swift-mcp-gui"
}
}
}
Available Tools
The server provides the following tools for controlling macOS:
1. Mouse Movement
- Tool name:
moveMouse - Input:
x: number (x-coordinate) - accepts integers, doubles, or string representationsy: number (y-coordinate) - accepts integers, doubles, or string representations
- Moves the mouse cursor to the specified coordinates
2. Mouse Clicks
- Tool name:
mouseClick - Input:
button: string ("left" or "right")
- Performs a mouse click at the current cursor position
3. Keyboard Input
- Tool name:
sendKeys - Input:
keys: array of strings (key names)
- Sends keyboard shortcuts or key combinations
- Example keys: "command", "control", "option", "shift", "return", "space", "a", "1", etc.
4. Scrolling
- Tool name:
scroll - Input:
direction: string ("up", "down", "left", "right")clicks: number (number of scroll clicks)
- Performs scrolling in the specified direction
5. Screen Size
- Tool name:
getScreenSize - Returns the main screen dimensions (width and height)
6. Pixel Color
- Tool name:
getPixelColor - Input:
x: number (x-coordinate) - accepts integers, doubles, or string representationsy: number (y-coordinate) - accepts integers, doubles, or string representations
- Returns the RGBA color values (0-255) of the pixel at the specified coordinates
7. Capture Screen
- Tool name:
captureScreen - Input:
quality: number (optional, 0.0-1.0, default: 0.1) - JPEG compression qualityscale: number (optional, 0.1-1.0, default: 0.25) - Scale factor for image size
- Captures the entire screen and returns it as a base64-encoded JPEG image
- Default settings (10% quality, 25% scale) optimize for fast processing and prevent timeouts
8. Capture Region
- Tool name:
captureRegion - Input:
x: number (x-coordinate of the region)y: number (y-coordinate of the region)width: number (width of the region)height: number (height of the region)quality: number (optional, 0.0-1.0, default: 0.1) - JPEG compression qualityscale: number (optional, 0.1-1.0, default: 0.25) - Scale factor for image size
- Captures a specific screen region and returns it as a base64-encoded JPEG image
- Default settings optimize for fast processing
9. Save Screenshot
- Tool name:
saveScreenshot - Input:
filename: string (path to save the screenshot)x: number (optional, x-coordinate of the region)y: number (optional, y-coordinate of the region)width: number (optional, width of the region)height: number (optional, height of the region)quality: number (optional, 0.0-1.0, default: 0.1) - JPEG compression qualityscale: number (optional, 0.1-1.0, default: 0.25) - Scale factor for image size
- Captures the screen or a region and saves it to a file
- File format is determined by the filename extension (.jpg, .jpeg, .png)
- Quality parameter only affects JPEG files
Security Considerations
This server requires full accessibility permissions in System Preferences to control your mouse and keyboard. Be careful when running it and only connect trusted MCP clients.
License
MIT License
Recommend MCP Servers 💡
n8n-workflow-manager
Manages n8n workflows within Docker containers, providing tools for listing, updating, backing up, and troubleshooting workflows.
browserloop
An MCP server that enables AI agents to capture high-quality screenshots and monitor console logs from web pages using Playwright, supporting various formats, authentication, and configurable options.
cronlytic-mcp-server
MCP server to let LLMs (AI Agents) communicate and interact with Cronlytic to perform CRUD operations for serverless cron jobs
patch-file-mcp
An MCP Server that allows AI agents to make precise changes to files using block format patches
mcp-server-macos-use
An MCP server in Swift that enables AI agents to control macOS applications using accessibility APIs, compatible with any model.
browser-control-mcp
MCP server paired with a browser extension that enables AI agents to control the user's browser.