Mac Commander

MCP server for macOS app automation, enabling AI tools to interact with applications through screenshots, OCR, and automation

typescript

13

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ohqay-mac-commander": {
      "command": "node",
      "args": [
        "/FULL/PATH/TO/mac-commander/build/index.js"
      ]
    }
  }
}

Available tools

screenshot

Capture a screenshot of the screen or a region with performance optimizations and optional base64 output.

list_screenshots

List all saved screenshots in the temporary folder.

view_screenshot

Display a specific saved screenshot by filename.

cleanup_screenshots

Remove old screenshots from the temporary folder, keeping the most recent ones.

compare_screenshots

Compare two saved screenshots to identify visual differences.

describe_screenshot

Capture and analyze a screenshot with AI-powered insights combining OCR and UI element detection.

performance_dashboard

Provide a real-time performance monitoring dashboard with health metrics and recommendations.

get_screen_info

Retrieve display dimensions and screen-related information.

check_for_errors

Scan the screen for common error indicators and dialogs.

wait

Pause execution for a specified duration.

diagnostic

Run a system health check to verify runtime readiness and environment.

find_text

Locate specific text on the screen using OCR with fuzzy matching and confidence scores.

extract_text

Extract on-screen text from regions or the entire screen with enhanced caching and accuracy.

find_ui_elements

Advanced visual detection of interactive UI components across multiple strategies.

click

Click at coordinates with configurable mouse button and optional verification.

type_text

Type text with adjustable keystroke delay.

mouse_move

Move the mouse to specified coordinates.

drag

Drag from one point to another using the mouse.

scroll

Scroll within a window or region in a specified direction.

hover

Hover the mouse at a position for a duration.

right_click

Right-click at coordinates to open context menus.

list_windows

List all open windows with titles and positions.

get_active_window

Get information about the currently active window.

find_window

Find a window by title with partial matching.

focus_window

Bring a window to the front by title.

get_window_info

Get detailed information about a specific window.

wait_for_element

Wait for specific text or UI element to appear on screen.