Browserbase

搜索与获取

by browserbasehq

Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to interact with web pages, take screenshots, and run parallel sessions in a cloud browser environment.

Verified

View Chinese version with editor review

Tools (9)

browserbase_session_create

Create or reuse a Browserbase browser session and set it as active.

browserbase_session_close

Close the current Browserbase session and reset the active context.

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_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_observe

Find interactive elements on the page from an instruction; optionally return an action.

browserbase_screenshot

Capture a full-page screenshot and return it (and save as a resource).

browserbase_stagehand_get_url

Return the current page URL (full URL with query/fragment).

browserbase_stagehand_agent

Execute a task autonomously using Gemini Computer Use agent. The agent will navigate and interact with web pages to complete the given task.

Related MCP Servers

Puppeteer

Browser automation with Puppeteer for web scraping and testing.

82.9k
Fetch

Fetch and convert web pages to markdown for AI-friendly consumption.

82.9k
Brave Search

Web and local search using the Brave Search API.

82.9k