How to Use the Puppeteer MCP Server for Web Scraping & Automation

Automate web browsers using the Puppeteer MCP server. Navigate websites, take screenshots, extract data, and automate web interactions through AI.

Puppeteerweb scrapingbrowser automationscreenshotstesting

Use the Puppeteer MCP Server for Web Automation

The Puppeteer MCP server allows AI agents to control a web browser, enabling web scraping, screenshots, form filling, and complex web automation tasks.

Prerequisites

▸Node.js 18+
▸Chrome/Chromium browser
▸Sufficient system memory (Puppeteer can be resource-intensive)

Installation

bash

npm install -g @modelcontextprotocol/server-puppeteer

Configuration

json

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-puppeteer"]
    }
  }
}

Available Tools

Tool	Description
code `puppeteer_navigate`	Navigate to a URL
code `puppeteer_screenshot`	Capture page screenshot
code `puppeteer_click`	Click an element
code `puppeteer_fill`	Fill form fields
code `puppeteer_select`	Select dropdown options
code `puppeteer_hover`	Hover over elements
code `puppeteer_evaluate`	Execute JavaScript on page

Example Workflows

Screenshot Capture

code

"Navigate to example.com and take a full-page screenshot"

Data Extraction

code

"Go to the pricing page of competitor.com and extract all plan details into a comparison table"

Form Automation

code

"Fill out the contact form on my-site.com with test data and submit it"

Visual Testing

code

"Take screenshots of my website at mobile, tablet, and desktop widths"

Advanced: JavaScript Evaluation

The

code

puppeteer_evaluate

tool lets you run arbitrary JavaScript in the browser context:

javascript

// Extract all product prices from a page
const prices = document.querySelectorAll('.price');
return Array.from(prices).map(p => p.textContent);

Best Practices

▸Respect robots.txt: Don't scrape sites that prohibit it
▸Rate limiting: Add delays between requests to be polite
▸Error handling: Pages may load differently each time
▸Resource management: Close the browser when done

Troubleshooting

▸
Chrome not found: Set the
code
```
PUPPETEER_EXECUTABLE_PATH
```
environment variable
▸Timeout errors: Increase navigation timeout for slow pages
▸Memory issues: Run in headless mode (default) to reduce memory usage