MCP.so
ログイン

MCP Browser Automation Server

@weir1

MCP Browser Automation Server について

MCP server for browser automation with screenshot and console logging capabilities

基本情報

カテゴリ

ブラウザ自動化

ランタイム

python

トランスポート

stdio

公開者

weir1

設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

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 MCP Browser Automation Server?

A simple browser automation server that lets you control browsers, take screenshots, and monitor console logs through a REST API and WebSocket. It is intended for developers who need programmatic control over browser sessions.

How to use MCP Browser Automation Server?

Clone the repository, create a virtual environment, install the Python dependencies from requirements.txt, install Playwright browsers with playwright install, then start the server with python server.py. Interact with it via the documented REST endpoints and WebSocket channel.

Key features of MCP Browser Automation Server

  • Create browser sessions.
  • Navigate to URLs.
  • Take screenshots (full page or specific element).
  • Click elements and fill form inputs.
  • Monitor console logs in real-time via WebSocket.
  • Close sessions.

Use cases of MCP Browser Automation Server

  • Automating web page interactions for testing.
  • Capturing screenshots of pages or elements.
  • Debugging client‑side code by watching console logs.
  • Filling and submitting forms programmatically.

FAQ from MCP Browser Automation Server

How do I install the server?

Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, then run playwright install to download browser binaries. Start the server with python server.py.

What runtime dependencies are required?

Python, the packages listed in requirements.txt, and Playwright (which downloads Chromium, Firefox, or WebKit).

How do I take a screenshot of a specific element?

Use the POST /session/{session_id}/screenshot endpoint with a selector query parameter (e.g., .my-element). If no selector is given, a full‑page screenshot is taken.

How can I monitor browser console logs?

Connect to the WebSocket endpoint at /session/{session_id}/console; the server streams console log messages in real‑time.

What transport and authentication are used?

The server uses REST (HTTP) for most operations and WebSocket for console log streaming. No authentication is described in the README.

コメント

「ブラウザ自動化」の他のコンテンツ