Browserbase MCP Server

Browser Automationstdiov1.2.0
代码仓库

Official Browserbase MCP server for cloud browser automation. Lets AI agents create headless browser sessions, navigate pages, extract content, take screenshots, and perform actions using Stagehand, enabling reliable web automation and scraping at scale from AI-powered tools.

browserbasebrowser-automationweb-scrapingstagehandheadless-browser

连接

将此配置添加到 .claude/mcp.json

{
  "mcpServers": {
    "browserbase": {
      "command": "npx",
      "args": [
        "-y",
        "@browserbasehq/mcp-server-browserbase"
      ],
      "env": {
        "BROWSERBASE_API_KEY": "<YOUR_BROWSERBASE_API_KEY>",
        "BROWSERBASE_PROJECT_ID": "<YOUR_BROWSERBASE_PROJECT_ID>"
      }
    }
  }
}

工具 (3)

browserbase_navigate

Open a URL in a cloud browser session and wait for it to load.

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to navigate to"
    }
  }
}

browserbase_extract

Extract structured content from the current page using a natural language instruction.

{
  "type": "object",
  "required": [
    "instruction"
  ],
  "properties": {
    "instruction": {
      "type": "string",
      "description": "What to extract from the page"
    }
  }
}

browserbase_screenshot

Capture a screenshot of the current page.

{
  "type": "object",
  "properties": {
    "full_page": {
      "type": "boolean",
      "description": "Whether to capture the full scrollable page"
    }
  }
}

资源

此服务器未提供任何资源。

提示词

此服务器未提供任何提示词。

服务器信息

作者
Browserbase (@browserbase)
代码仓库
https://github.com/browserbase/mcp-server-browserbase
许可证
Apache-2.0
版本
1.2.0
星标
1,123
最后更新
2026年7月9日