Browserbase
Allow LLMs to control a browser with Browserbase and Stagehand for AI-powered web automation, intelligent data extraction, and screenshot capture.
204
8 Tools
Packaged by
Requires Secrets
Add to Docker Desktop
Version 4.43 or later needs to be installed to add the server automatically
Tools
| Name | Description |
|---|---|
browserbase_screenshot | Capture a full-page screenshot and return it (and save as a resource). |
browserbase_session_close | Close the current Browserbase session and reset the active context. |
browserbase_session_create | Create or reuse a Browserbase browser session and set it as active. |
browserbase_stagehand_act | Perform a single action on the page (e.g., click, type). |
browserbase_stagehand_extract | Extract structured data or text from the current page using an instruction. |
browserbase_stagehand_get_url | Return the current page URL (full URL with query/fragment). |
browserbase_stagehand_navigate | Navigate to a URL in the browser. Only use this tool with URLs you're confident will work and be up to date. Otherwise, use https://google.com as the starting point |
browserbase_stagehand_observe | Find interactive elements on the page from an instruction; optionally return an action. |
Manual installation
You can install the MCP server using:
Installation for