Create a new Chrome browser instance and return session_id (UUID)

Close a specific Chrome browser instance by session_id, will delete the instance and all related data

Get detailed information about a specific browser instance

Check the health status of a browser session and provide recovery suggestions

Get current browser status, including all instances and their status,only admin can use this tool

Close all browser instances and delete all related data, only admin can use this tool

Set advanced browser configuration for a specific instance. If you want to change the viewport, you can use the set_browser_config tool to change the viewport_width and viewport_height.

Get advanced browser configuration for a specific instance

Navigate to URL in current tab or new tab (does not auto-switch to new tab).

Go back in current tab's history.

Navigate forward in browser history

Refresh the current page

Get current page state and interactive elements; frames mode is unstable and may not extract all details.

Get information about all open browser tabs

Close a specific tab, if the tab is the last one, it will goto about:blank

Switch to a specific browser tab and return the tab info object

Click an interactive element by XPath with confirmation

Click an interactive element by index with confirmation

Input text into a form field

Set value of an input or select element directly, supports frames

Get detailed information about a DOM element (supports index or xpath query), can get the value of the element

Send keyboard keys to the browser

Scroll page up or down

Upload file to file input element

Generate PDF from current page, URL, or HTML content

Take screenshot with structured result, it will take screenshot of the target element if target is not None, otherwise it will take screenshot of the full page, otherwise it will take screenshot of the current viewport Screenshot page or element (by target selector, supports CSS/XPath, e.g. 'button', '//button', 'css=button', 'xpath=//button'). See: https://playwright.dev/python/docs/locators#locate-by-css-or-xpath

Download any file from URL to the temp directory. Use fetch+blob+a.download, if failed, fallback to goto+expect_download, maximum compatibility.

Download a image from URL, it will download the image to the temp directory, and return the file path, it will open a new tab if the image is not from the same origin as the current page

Set a cookie in the browser

Get cookies from the browser

Wait for specified number of seconds with progress

Search Bing for a query with progress tracking

Extract content from page based on query, including all frames/iframes

Get options from a dropdown/select element, it will return the options of the element, and the id and name of the element

LLM-oriented best practices and practical tips for robust, step-by-step use of browser MCP tools.