Open a URL in the browser and return the page context (DOM elements + OCR text). Default text-only mode — screenshot is captured only for OCR then discarded, zero image tokens. Set visual=true to also receive the PNG.

Click an element on the current page. Identify the target by CSS selector, XPath, or visible text. Returns updated page context after the click.

Type text into an input field on the current page. By default clears the field first. Returns updated page context.

Scroll the current page. Use direction (up/down/left/right) with an optional pixel amount, or provide a selector to scroll that element into view.

Capture the current page and return an OCR-based text map. The screenshot itself is discarded unless visual=true.

Read the current page context (DOM elements + OCR text) without navigating or clicking anything.

Execute JavaScript in the current page context and return the result. Restricted to safe DOM read operations — eval, Function, fetch, WebSocket, and document.write are blocked.