Browser Use MCP Server

@co-browser

リポジトリホームページ

基本情報

カテゴリ

ブラウザ自動化

ライセンス

MIT

トランスポート

stdio

作者

co-browser

Browser Use MCP Server について

Browse the web, directly from Cursor etc.

#browser #mcp #cursor #playwright #mcp-server #browser-use

Browser Use MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "browser-use-mcp-server": {
      "command": "uv",
      "args": [
        "tool",
        "install",
        "mcp-proxy"
      ]
    }
  }
}

Browser Use MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is browser-use-mcp-server?

An MCP server that enables AI agents to control web browsers using the browser-use library. It is designed for developers building AI-powered browser automation workflows.

How to use browser-use-mcp-server?

Install prerequisites (uv, Playwright, mcp-proxy), set environment variables in a .env file (OPENAI_API_KEY, CHROME_PATH, PATIENT), then run the server in either SSE mode (uv run server --port 8000) or stdio mode after building and installing the package. Configure your MCP client (Cursor, Windsurf, Claude) with the appropriate JSON configuration.

Key features of browser-use-mcp-server

Control browsers through AI agents
Support for both SSE and stdio transport protocols
Real-time VNC streaming of browser automation
Execute browser operations asynchronously
Docker support for consistent isolated environment

Use cases of browser-use-mcp-server

Ask an AI to navigate a website and retrieve information, such as "open https://news.ycombinator.com and return the top ranked article"
Automate multi-step web tasks like form filling or data extraction
Watch browser automation in real-time via VNC streaming
Run browser agents in a Docker container for reproducibility

よくある質問

What are the prerequisites for browser-use-mcp-server?

You need uv (Python package manager), Playwright (browser automation), and mcp-proxy (for stdio mode). Install them with `curl -LsSf https://astral.sh/uv/install

「ブラウザ自動化」の他のコンテンツ

Chrome DevTools for agents

ChromeDevTools

Official Chrome DevTools MCP server from Google that lets coding agents control, debug and profile a live Chrome browser.

53.6K

Fastcrw

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

286