Puppeteer

Name: Puppeteer
Author: jatidevelopments

@jatidevelopments

リポジトリ

Puppeteer について

Advanced Puppeteer automation server with enhanced functionality (MCP Server)

#puppeteer #browser-automation #automation-server

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

node

トランスポート

stdio

公開者

jatidevelopments

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-puppeteer-advanced": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp/puppeteer",
        "-f",
        "Dockerfile",
        "."
      ]
    }
  }
}

ツール

Navigate to any URL in the browser

Capture screenshots of the entire page or specific elements

Click elements on the page

Hover elements on the page

Fill out input fields

Select an element with SELECT tag

Execute JavaScript in the browser console

Extract all images from the page (both `<img>` tags and CSS background images)

Download extracted images to a specified folder

Analyze a DOM element to extract its HTML structure, Markdown representation, and applied styles

Check browser status, list open tabs, and manage tab switching

Analyze the DOM hierarchy of a page and determine parent-child relationships between elements

Switch the browser viewport to simulate different devices (mobile, tablet, desktop)

Navigate back or forward in browser history

概要

What is Puppeteer?

Puppeteer is a Model Context Protocol server that provides browser automation capabilities using Puppeteer. It enables LLMs to interact with web pages, take screenshots, extract and download images, and execute JavaScript in a real browser environment.

How to use Puppeteer?

Configure the server in your MCP client using either Docker (docker run -i --rm --init -e DOCKER_CONTAINER=true mcp/puppeteer) or NPX (npx -y @modelcontextprotocol/server-puppeteer). Customize Puppeteer’s browser behavior via the PUPPETEER_LAUNCH_OPTIONS environment variable or by passing launchOptions and allowDangerous to the puppeteer_navigate tool.

Key features of Puppeteer

Browser automation and console log monitoring
Screenshot capture of entire pages or specific elements
JavaScript execution in the browser console
Web interaction (navigation, clicking, form filling)
Image extraction from <img> tags and CSS backgrounds
Multi-tab browser management and viewport switching

Use cases of Puppeteer

Extract and download all images from a webpage
Analyze DOM elements to retrieve HTML, Markdown, and styles
Test responsive design by switching viewport presets (mobile, tablet, desktop)
Manage multiple browser tabs: open, list, switch, and take actions in each
Navigate browser history (back/forward) and execute custom scripts

FAQ from Puppeteer

What tools does Puppeteer provide?

Puppeteer offers tools for navigation, screenshots, clicking, hovering, form filling, selecting, evaluating JavaScript, extracting/downloading images, analyzing DOM elements and page hierarchy, managing browser tabs, switching viewports, and navigating history.

How can I customize browser launch options?

Set the PUPPETEER_LAUNCH_OPTIONS environment variable as a JSON-encoded string, or pass launchOptions and allowDangerous parameters directly to the puppeteer_navigate tool.

What resources are available?

Two resource types: console://logs (browser console output) and screenshot://<name> (PNG images of captured screenshots).

Can I run Puppeteer in Docker?

Yes. Use the Docker configuration shown in the README. The Docker version runs headless Chromium, while the NPX version opens a browser window.

Does Puppeteer support dangerous launch options?

Yes, but they are disabled by default. Set allowDangerous to true (either in the environment via ALLOW_DANGEROUS or in the tool call) to use options like --no-sandbox or --disable-web-security.