Puppeteer MCP Server (Python Implementation)

Name: Puppeteer MCP Server (Python Implementation)
Author: twolven

@twolven

Puppeteer MCP Server (Python Implementation) について

MCP server providing browser automation via Playwright (Python), enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser.

基本情報

カテゴリ

ブラウザ自動化

ライセンス

Apache-2.0

ランタイム

python

トランスポート

stdio

公開者

twolven

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-server-puppeteer-py": {
      "command": "python",
      "args": [
        "puppeteer_server.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 Puppeteer MCP Server (Python Implementation)?

A Model Context Protocol server that provides browser automation capabilities using Playwright (Python's equivalent to Puppeteer). It enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

How to use Puppeteer MCP Server (Python Implementation)?

Install the required packages with pip install -r requirements.txt, then install Playwright browsers using playwright install. Start the server by running python puppeteer_server.py, or configure it in Claude Desktop by adding a JSON entry with command "python" and args pointing to the server script.

Key features of Puppeteer MCP Server (Python Implementation)

Full browser automation capabilities
Page navigation to any URL
Screenshot capture of entire page or specific elements
Form interaction (clicking and filling fields)
JavaScript execution in the browser console
Configurable timeouts and detailed error handling
Comprehensive logging (INFO, ERROR, DEBUG levels)

Use cases of Puppeteer MCP Server (Python Implementation)

Automate web browsing tasks for LLM agents to gather information
Capture screenshots of web pages or specific elements for analysis
Programmatically fill forms and click buttons on websites
Execute custom JavaScript to extract data from dynamic pages
Monitor console logs during automated browser sessions

FAQ from Puppeteer MCP Server (Python Implementation)

What are the prerequisites for Puppeteer MCP Server (Python Implementation)?

Python 3.8+ and pip are required. Additionally, Playwright browsers must be installed using playwright install.

Does the browser run in headless mode?

No, the browser launches in non-headless mode for better debugging.

What is the default viewport size?

The default viewport size is 1280x720.

How are screenshots stored?

Screenshots are stored in memory with base64 encoding.

How does error handling work?

The server provides detailed error messages for navigation failures, element not found, timeout errors, JavaScript execution errors, and screenshot failures.

「ブラウザ自動化」の他のコンテンツ

Fetch MCP

jae-jae

MCP server for fetch web page content using Playwright headless browser.

1.1K

Fetch

modelcontextprotocol

Model Context Protocol Servers

88.1K

App Store Scraper MCP Server

appreply-co

This is an MCP server that provides tools to LLMs for searching and analyzing apps from both Google Play Store and Apple App Store – perfect for ASO.

Puppeteer MCP Server

merajmehrabi

This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.

474

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