MCP.so
ログイン

Playwright MCP Server

@san0808

Playwright MCP Server について

This server provides a comprehensive set of tools to control a web browser instance using Playwright, exposed via the Model Context Protocol (MCP). It allows AI models or other MCP clients to perform complex web browsing tasks across multiple pages/tabs.

基本情報

カテゴリ

ブラウザ自動化

ライセンス

MIT license

ランタイム

python

トランスポート

stdio

公開者

san0808

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": {
    "playwright_mcp_server": {
      "command": "python",
      "args": [
        "client_example.py"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 Playwright MCP Server?

This server provides a comprehensive set of tools to control a web browser instance using Playwright, exposed via the Model Context Protocol (MCP). It allows AI models or other MCP clients to perform complex web browsing tasks across multiple pages/tabs.

How to use Playwright MCP Server?

Install the Python dependencies (pip install "fastmcp>=2.0.0" playwright) and install Playwright’s Chromium browser (playwright install chromium). Run the server via the FastMCP CLI, e.g. fastmcp run main.py --transport sse --port 8001, then execute the provided client example script.

Key features of Playwright MCP Server

  • Multi-page management: open, close, switch, and list pages
  • Navigation: go to URLs, back/forward, reload
  • Content retrieval: HTML, text, title, URL
  • Full interaction suite: click, fill, type, check, select, hover, drag-and-drop
  • Waiting utilities: for elements, URLs, load states
  • State/information: element visibility, attributes, bounding box
  • Visuals: page and element screenshots

Use cases of Playwright MCP Server

  • Web scraping and content extraction from dynamic pages
  • Automated form filling and interactive testing
  • Multi-tab browsing workflows for AI agents
  • Visual regression testing via screenshots
  • JavaScript evaluation for deep page analysis

FAQ from Playwright MCP Server

What dependencies does Playwright MCP Server require?

Python 3.x, the fastmcp>=2.0.0 and playwright packages, and the Playwright Chromium browser installed via playwright install chromium.

How do I run the server?

Use the FastMCP CLI: fastmcp run main.py --transport sse --port 8001. Alternatively, a client example using stdio transport is included.

Are there security concerns with the JavaScript evaluation tools?

Yes, playwright_evaluate and playwright_execute_javascript are powerful and can execute arbitrary code. Use with caution or disable them if the server is exposed publicly.

What transports are supported?

The server can be run with SSE (WebSocket) or stdio transport, as shown in the usage examples.

What license is Playwright MCP Server distributed under?

MIT License.

コメント

「ブラウザ自動化」の他のコンテンツ