Enables macOS computer-use automation through public Apple APIs, supporting app and window discovery, clicking, typing, scrolling, and field setting via accessibility controls.
Enables MCP clients to inspect and operate native macOS apps through the Accessibility tree with safety-gated semantic actions, stale-state rejection, and outcome verification. Supports tools for app state reading, element finding, clicking, typing, form filling, window capture, and guarded workflows like menu selection and Save As.
Provides native macOS desktop automation for AI agents, enabling screen capture, mouse/keyboard control, window management, and iOS/Android simulator control in both foreground and background modes without focus stealing.
Enables agents to inspect and control macOS applications through Accessibility trees, screenshots, and OCR. It supports clicks, typing, key presses, scrolling, drags, clipboard paste, window actions, and scripted actions via MCP.