Exposes a remote browser as MCP tools via Playwright, enabling AI agents to navigate and interact with web pages through DOM snapshots, clicks, typing, and form operations.
Enables local AI models to control a remote Windows desktop over RDP by viewing screenshots and injecting mouse and keyboard input, with no software installed on the remote host.
Enables AI agents to see and control an existing Linux X11 desktop over SSH by taking screenshots and performing mouse, scroll, typing, and keyboard-shortcut actions across browsers, terminals, file managers, and other apps.
Enables recording live website behavior on a rented GPU VM via Playwright, capturing page load, scroll, and optional hover/click actions into WebM video with jank reports, then copying the artifacts locally.
Enables browser automation through Playwright with persistent sessions and cookie state management. Supports web navigation, page interaction, and browser control via JSON-RPC protocol over stdin/stdout.