Connect to an existing Chrome browser via CDP and extract auth cookies. Chrome must be running with --remote-debugging-port. This also extracts cookies/storage so new instances can be created without re-login.

Create a new isolated browser instance. Auth (cookies/localStorage) is automatically cloned from the connected Chrome, so no re-login is needed. Each instance has fully isolated state.

List all active browser instances with their current URLs and titles.

Close a specific browser instance and release its resources.

Close all browser instances.

Navigate an instance to a URL.

Take an accessibility snapshot of the page. Returns a structured text representation with refs for interactive elements. Always use this before performing actions to understand the current page state.

Click an element identified by ref from the latest page_snapshot.

Clear and fill text into an input element identified by ref.

Type text into editable element. By default fills at once; set slowly=true to type character by character.

Select option(s) in a element.

Hover over an element.

Press a key or key combination (e.g. "Enter", "Control+a", "Escape").

Take a screenshot of the page or a specific element.

Wait for text to appear, disappear, or a specified time.

Evaluate a JavaScript expression in the page context. Returns JSON-serializable result.

Maximize the browser window for an instance via CDP protocol.

Go back to the previous page in history.

Resize the browser viewport for an instance.

Drag an element and drop it onto another element.

Upload one or multiple files via a file input element.

Fill multiple form fields at once.

Handle a browser dialog (alert, confirm, prompt). Must be called when a dialog is open.

Return all console messages captured from the page.

Return all network requests since the page was loaded.

Run a Playwright code snippet against the instance page. For advanced use cases.

Click at specific coordinates on the page.

Move the mouse to specific coordinates.

Drag from one point to another using coordinates.

Save the page as a PDF file.

Verify that text is visible on the page.

Verify that an element with a specific role and name is visible.

Verify the value of a form element.

Generate a Playwright locator string for the given element, useful for test code generation.

Start a Playwright trace recording for debugging.

Stop the trace recording and save to file.