Puppeteer lets programs open a browser on their own, clicking buttons, typing text, and scraping page content just like a human—so you don’t have to watch it work. With 95k stars on GitHub, it’s the undisputed benchmark project in browser automation. GitHub: https://github.com/puppeteer/puppeteer… In the past, manually logging into a website every day to scrape data, fill forms, or test a web feature required endless repetitive clicking. Screen‑recording macros were fragile and broke whenever the page changed. After switching to Puppeteer, a few lines of code can control Chrome or Firefox—simulate clicking the search box, entering keywords, clicking results, and grabbing page text. The whole process runs headless by default and can be left to finish in the background without human supervision. Even more interesting, it has MCP: the Chrome DevTools MCP server built by Puppeteer allows AI agents to control and debug the browser directly via the MCP protocol. That means it’s no longer just programmers writing automation scripts—AI agents can also use Puppeteer as their hands to interact with web pages.

puppeteer/puppeteer

Source: https://github.com/puppeteer/puppeteer

Puppeteer

build npm puppeteer package

Puppeteer is a JavaScript library that provides a high-level API to control Chrome or Firefox over the DevTools Protocol or WebDriver BiDi. By default, Puppeteer runs in headless (no visible UI) mode.

Get started | API | FAQ | Contributing | Troubleshooting

Installation

npm2yarn npm i puppeteer
# Downloads a compatible version of Chrome during installation.
npm i puppeteer-core
# Alternatively, install as a library, without downloading Chrome.

:::note Modern package managers (including npm (see the RFC), pnpm, Yarn, Bun, and Deno) block dependency install scripts by default. If the install script is blocked, Puppeteer will not download the browser during installation, causing runtime errors. You can manually download the required browsers after installation by running:

npm2yarn npx puppeteer browsers install

Alternatively, you can configure your package manager to allow the install script to run (for example, with npm, by adding "puppeteer" to "allowScripts" in your package.json). :::

MCP

Install chrome-devtools-mcp, a Puppeteer-based MCP server for browser automation and debugging. Puppeteer also supports the experimental WebMCP API.

Example

import puppeteer from 'puppeteer';
// Or import puppeteer from 'puppeteer-core';

// Launch the browser and open a new blank page.
const browser = await puppeteer.launch();
const page = await browser.newPage();

// Navigate the page to a URL.
await page.goto('https://developer.chrome.com/');

// Set the screen size.
await page.setViewport({width: 1080, height: 1024});

// Open the search menu using the keyboard.
await page.keyboard.press('/');

// Type into search box using accessible input name.
await page.locator('::-p-aria(Search)').fill('automate beyond recorder');

// Wait and click on first result.
await page.locator('.devsite-result-item-link').click();

// Locate the full title with a unique string.
const textSelector = await page
  .locator('::-p-text(Customize and automate)')
  .waitHandle();
const fullTitle = await textSelector?.evaluate(el => el.textContent);

// Print the full title.
console.log('The title of this blog post is "%s".', fullTitle);

await browser.close();