BrowserbaseをChatGPT、Claude、Geminiに接続

• 01 / 02ブラウザ操作の自動化について
• 02 / 02ブラウザセッションの監視方法

最速日

704ms

最遅日

976ms

14日間の傾向

遅延傾向+7%

Browserbase Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_RnYZgVbXYpn0PHnLYtDs7Cz7jgbxWTQ7qs7Q34up/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — Browserbase capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "browserbase-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_RnYZgVbXYpn0PHnLYtDs7Cz7jgbxWTQ7qs7Q34up/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ BrowserbaseをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  AIエージェント開発者

  ログインやフォーム入力、SPAの操作など、複雑なWebインタラクションをAIに行わせたい方。

• 02

  QA自動化エンジニア

  独自のインフラを構築することなく、ブラウザベースのテストを大規模に実行したい方。

• 03

  Webスクレイピング担当者

  JavaScriptの実行や認証、複雑なナビゲーションが必要なコンテンツへのアクセスを自動化したい方。

• 01

  How do I connect my agent to the browser?

  The MCP provides a CDP WebSocket URL after a session is created. You use this URL with automation libraries like Playwright, Puppeteer, or Selenium to control the browser.

• 02

  What browsers are supported?

  This MCP provides access to headless Chromium sessions in the cloud.

• 03

  Can I see if my browser sessions are still running?

  Yes, you can use the capability to list all sessions or get specific details for a single session ID to check its status.

• 04

  How do I stop a session?

  You can use the capability to stop a specific session by its ID, which terminates the process and frees up resources.

• 05

  Is there a way to test this for free?

  Browserbase includes 1 free browser hour when you enter your API key.

• 06

  How is Browserbase different from Firecrawl?

  Firecrawl is optimized for content extraction. it scrapes pages and returns clean data. Browserbase provides a full browser environment for interactive automation. your agent can click buttons, fill forms, log into websites, scroll, and navigate complex single-page applications (SPAs). Browserbase gives you a real browser, Firecrawl gives you the text from a page.

• 07

  Which automation frameworks are supported?

  Browserbase sessions expose a CDP (Chrome DevTools Protocol) WebSocket URL, which is compatible with all major browser automation frameworks: Playwright, Puppeteer, Selenium WebDriver, and any capability that supports CDP connections. Simply point your framework at the connectUrl returned when creating a session.

• 08

  What does the free tier include?

  The free tier includes 1 browser hour, 1 concurrent browser session, and 7 days of data retention. No credit card required. For production workloads, paid plans start at $20/month (Developer) with more browser hours and concurrent sessions.

• 

  Browserless (Playwright Cloud) AIコネクタ

  Equip your AI with a remote headless browser to scrape, interact, and run Playwright safely via cloud.

  表示
• 

  Browserless AIコネクタ

  Manage headless Chrome via Browserless — take screenshots, generate PDFs, and scrape web content directly from

  表示
• 

  Hyperbrowser (Web Infra for AI) AIコネクタ

  Cloud browsers for AI agents via Hyperbrowser — manage sessions, scrape pages, and extract structured data.

  表示
• 

  Modal (Serverless AI Infrastructure) AIコネクタ

  Manage serverless compute via Modal — audit active apps, track GPU deployments, and monitor network volumes.

  表示

おすすめ

• 

  Browserbear AIコネクタ

  Automate browser tasks via Browserbear — take screenshots, scrape data, and run multi-step automations directl

  表示
• 

  Apify AIコネクタ

  Command Apify scrapers from your AI agent — run actors, extract web data, poll datasets, and automate browser

  表示
• 

  BrowserStack AIコネクタ

  Automate testing via BrowserStack — manage projects, track test builds, fetch session logs, and monitor execut

  表示
• 

  ParseHub AIコネクタ

  Control advanced cloud scraping projects via ParseHub — list targets, dispatch headless runs, trace crawler st

  表示