What the agent can do
Drive the page
Open a URL — with mobile emulation when you need it — in the built-in browser.
Full interaction: navigate/back/forward, click (including double-click and specific mouse buttons), type text and keys, hover, and drag between elements.
Handle JavaScript dialogs and native file pickers — including selecting files for upload.
Fill a whole form in one call.
See and extract
read_page · extract_page_data · screenshot_page
Read page content, pull structured data with a focus hint, or screenshot the page or a single element.
get_computed_styles · watch_page
Inspect an element’s computed CSS, or wait for the page to reach a condition before continuing.
Inspect like a developer
get_browser_console_logs · intercept_network · get_browser_network_log
Read the console, intercept requests by URL pattern (optionally with bodies), and pull the network log — the tools you’d use to understand or reverse-engineer how a site actually works.
Reconstruct a live page’s sources into files — the basis for cloning a site pixel-perfect, bundling it out of the browser, or studying how it’s built.
Go beyond the built-ins
Run arbitrary Playwright code against the page for anything the named tools don’t cover.
save_browser_session · restore_browser_session
Save and restore a browser session, so the agent can stay logged in across runs instead of re-authenticating every time.