Browser automation with Puppeteer for web scraping and testing
The Puppeteer MCP Server enables browser automation through your AI assistant. Navigate to URLs, take screenshots, click elements, fill forms, and execute JavaScript in the browser. Useful for web scraping, testing, and automating browser tasks.
Is it safe?
No known CVEs for @modelcontextprotocol/server-puppeteer.
No authentication — any process on your machine can connect to this server.
MIT. View license →
Last scanned 0 days ago.
Is it maintained?
Last commit 5 days ago. 82,845 GitHub stars. 27,305 weekly downloads.
Will it work with my client?
Transport: stdio. Works with claude-desktop, cursor, claude-code, windsurf.
How much context will it use?
5 tools. Estimated ~100 tokens of your context window (0.1% of 200K).
What if it doesn't work?
Common issues: JSON syntax errors in config, wrong Node.js version, npx cache. Setup guide covers troubleshooting. Or check GitHub issues for known problems.
{
"mcpServers": {
"puppeteer": {
"args": [
"-y",
"@modelcontextprotocol/server-puppeteer"
],
"command": "npx"
}
}
}Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y @modelcontextprotocol/server-puppeteer 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
puppeteer_navigateNavigate to a URL
puppeteer_screenshotTake a screenshot
puppeteer_clickClick an element
puppeteer_fillFill out an input field
puppeteer_evaluateExecute JavaScript in the browser
Last scanned 1h ago
No known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.