Activate browser automation. Required first step before any browser interaction.

Deactivate browser automation and disconnect from browser extension

Check current connection status and browser state

Manage browser tabs: list, create, attach, or close tabs

Navigate to URL, back, forward, or reload page

Get accessible DOM snapshot of the page (fast, text-based)

Capture screenshot with optional overlays, element highlighting, or partial capture

Extract page content as clean markdown with smart content detection

Perform one or more interactions: click, type, hover, scroll, drag, wait, file upload, and more

Fill multiple form fields at once with smart field matching

Execute JavaScript in page context

Get browser console messages with filtering

Monitor and replay network requests with JSONPath filtering

Manage browser window: resize, minimize, maximize, close

Save current page as PDF

Handle alert/confirm/prompt dialogs

Get Web Vitals and performance metrics

Verify text is visible on page (for testing)

Verify element is visible on page (for testing)

List installed browser extensions

Reload unpacked/development browser extensions

🆕 Get visual map of interactive elements with numbered overlays. Shows a screenshot where every clickable element has a number badge. Use "click(42)" style references.

🆕 Get a clean JSON map of ALL interactive elements with IDs, types, labels, and positions. Perfect for AI understanding of page layout.

🆕 Get detailed information about specific elements including computed styles, accessibility info, and state

🆕 Auto-detect and classify page components: forms, navigation, ads, popups, modals, cookie banners, tables, etc.

🆕 Auto-detect form fields and fill them intelligently based on field labels, names, and types

🆕 Get detailed analysis of all forms on page including field types, labels, required status, and validation rules

🆕 Click an element by its overlay ID from the visual map

🆕 Hover over an element by its overlay ID from the visual map

🆕 Detect and handle popups, modals, cookie banners, and notifications

🆕 Detect ad elements on the page with detailed information

🆕 Get, set, or delete browser cookies

🆕 Access and modify localStorage and sessionStorage

🆕 Smart wait for elements, text, or conditions with retry

🆕 Find the best matching element when a selector fails, using fuzzy matching on text, role, and attributes

🆕 Get the full accessibility tree with ARIA roles, names, and states (screen reader view)

🆕 Detect if a CAPTCHA or bot verification is present on the page

🆕 Auto-detect login forms and provide structured information about username/password fields

🆕 Smart scroll with lazy loading support, can scroll to specific elements or areas

🆕 Visual diff between current page state and a previous screenshot or URL

Drag element to another element

Manage PRO authentication