Control mouse, keyboard, and screen for cross-platform desktop automation.

• Five command categories: mouse control (movement, clicks, drag, scroll), keyboard input (typing, hotkeys, key presses), screen capture and analysis (screenshots, image/text location via OCR), message dialogs (alerts, confirmations, prompts), and application control (open, focus, list windows)
• Supports Windows, macOS, and Linux with platform-specific shortcuts and application launching
• Image location with configurable confidence thresholds and OCR-based text finding within specific windows or active windows
• All commands output structured JSON for reliable programmatic parsing by AI agents, with detailed error codes and recoverable error handling
• Includes safety patterns: verify screen state before clicking, use window-specific screenshots for performance, validate element existence before interaction, and confirm destructive actions with user dialogs