Enables AI assistants to execute terminal commands on a host machine with configurable, granular permission controls and safety protections. It features multiple security modes, including allowlists and manual approval, to ensure safe command execution within specified directories.
Enables AI agents to run JavaScript in fresh V8 isolates and shell commands under macOS seatbelt sandboxing, with per-call permissions for network, CPU, memory, disk, and host mounts. It also supports persistent writable copies with explicit sync or discard for safe host directory edits.
Enables an AI agent to safely observe and operate a Mac, starting read-only with optional read-write and admin tools for files, processes, apps, shell, AppleScript, and GUI control behind explicit permissions and human approval.
Provides full control of a macOS system, enabling AI agents to execute shell commands, run AppleScript, manage files and processes, and perform human-like GUI interactions such as clicking, dragging, scrolling, and typing, with a screenshot-based perception loop.
Enables AI agents to call native macOS calendars, reminders, files, desktop/system actions, selected Apple apps, shortcuts, and web tools through MCP, with scoped file access and explicit approvals for writes.