Set it up
- 1
Turn on Puppeteer in your AI
In Claude: open Settings → Connectors and add Puppeteer. In ChatGPT: Settings → Apps & Connectors.
- 2
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Puppeteer.
- 3
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“Take a screenshot of https://example.com and save it to ./screenshot.png”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
}
}
}Paste into your client's MCP configuration file.
Quick skills
Copy one, paste it to your AI, watch it work.
Page Screenshots
“Take a full-page screenshot of https://example.com/dashboard and save it to ./screenshots”
PDF Generation
“Generate a PDF of https://example.com/report/2026-q1 and save it as q1-report.pdf”
Scraping with JS
“Go to this infinite-scroll product page, scroll to load 50 items, and extract their names and prices”
In the wild
“launch UI servers and use Puppeteer MCP to check the browser”
Good to know
- · Chromium has to be installed — the first run may download a few hundred MB
- · Running in headful mode opens real browser windows on your desktop
- · Some sites block headless browsers — you may need to tweak user agents
When to use
- ✓ You need to take screenshots of web pages
- ✓ You want to generate PDFs from HTML or live pages
- ✓ You're doing local scraping that requires JavaScript execution
- ✓ You want browser automation without cloud costs
When not to use
- × You need cloud-hosted browsers — use browserbase-mcp
- × You only need static HTML — fetch-mcp is simpler
- × You need cross-browser testing — use playwright-mcp (supports more engines)
About
Imagine asking your AI: 'Take a screenshot of this page' or 'Generate a PDF of this report URL' — and it runs a real Chrome browser locally to do it. This server lets your AI drive Puppeteer-controlled Chromium on your machine for screenshots, PDFs, scraping, and automation.
The official Puppeteer MCP server provides browser automation capabilities to AI assistants. Navigate URLs, take screenshots, interact with web elements, fill forms, click buttons, and extract page content — using a real Chromium browser.
One of the most powerful MCP servers for web scraping, UI testing, and automated browser workflows.
Workflows That Use Puppeteer MCP
Recommended recipe
Let Claude search and browse the live webReal-time search, page scraping, and full browser automation — Claude works with what's on the web right now.
Works With
Also Consider
FAQ
What does Puppeteer MCP do? +
Imagine asking your AI: 'Take a screenshot of this page' or 'Generate a PDF of this report URL' — and it runs a real Chrome browser locally to do it. This server lets your AI drive Puppeteer-controlled Chromium on your machine for screenshots, PDFs, scraping, and automation.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Puppeteer MCP? +
Reach for it when you need to: You need to take screenshots of web pages; You want to generate PDFs from HTML or live pages; You're doing local scraping that requires JavaScript execution; You want browser automation without cloud costs.
When should I avoid Puppeteer MCP? +
Skip it when: You need cloud-hosted browsers — use browserbase-mcp; You only need static HTML — fetch-mcp is simpler; You need cross-browser testing — use playwright-mcp (supports more engines).
How do I install Puppeteer MCP? +
In Claude Code, run: claude mcp add puppeteer -- npx -y @modelcontextprotocol/server-puppeteer. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.
