広告掲載
MCP.so
ログイン

MCP Web Browser Server

@random-robbie

リポジトリ

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

random-robbie

MCP Web Browser Server について

An advanced web browsing server for the Model Context Protocol (MCP) powered by Playwright, enabling headless browser interactions through a flexible, secure API.

MCP Web Browser 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": {
    "mcp-web-browser": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

MCP Web Browser 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 MCP Web Browser Server?

MCP Web Browser Server is an advanced headless browsing server for the Model Context Protocol, powered by Playwright. It enables secure, programmatic browser interactions through a flexible API, making it suitable for developers who need to automate web tasks or extract data.

How to use MCP Web Browser Server?

Install the server with pip install mcp playwright and then run playwright install to install browser dependencies. Configure it for Claude Desktop by adding a JSON entry in claude_desktop_config.json that points to the server script. Use Python code to invoke tools like browse_to, click_element, and get_page_screenshots.

Key features of MCP Web Browser Server

  • Headless web browsing with SSL validation bypass
  • Full page content extraction including JavaScript-rendered content
  • Multi-tab creation, management, and switching
  • Click elements, input text, and capture screenshots
  • Extract page links with optional filtering
  • Scroll pages and execute JavaScript on pages

Use cases of MCP Web Browser Server

  • Automate form filling and login flows on websites
  • Extract structured data from dynamic web pages
  • Capture full-page or element-specific screenshots for testing
  • Conduct multi-tab research by opening and switching between pages
  • Perform automated web UI regression checks with headless browsing

よくある質問

1

What are the runtime requirements for MCP Web Browser Server?

Python 3.10 or higher, MCP SDK, Playwright, and browser dependencies installed via `playwright install`.

2

How is MCP Web Browser Server configured for Claude Desktop?

Add an entry to `claude_desktop_config.json` with the command `python` and the path to the server script as an argument.

3

What happens to browser resources after a period of inactivity?

Unused browser resources are automatically cleaned up to free memory and prevent resource leaks.

4

Does MCP Web Browser Server handle SSL certificate errors?

Yes, SSL certificate validation is automatically bypassed during navigation.

5

Can I use multiple browser tabs simultaneously?

Yes, the server provides tools to create, list, switch between, and close multiple tabs.

コメント

「ブラウザ自動化」の他のコンテンツ

playwright-server MCP server

blackwhite084

189

browser-use-mcp-server

co-browser

Browse the web, directly from Cursor etc.

827

Firecrawl Mcp Server

mendableai

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

6.9K

HTML/CSS to Image

An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.

TinyFish

tinyfish

Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.

3
広告掲載