The original Chromium automation reference server — simple, screenshot-driven browser control.
The Puppeteer MCP server was one of the first reference servers Anthropic shipped alongside the Model Context Protocol, and it's still the quickest way to understand what browser automation over MCP feels like. It wraps Google's Puppeteer library around a headless (or headful) Chromium and exposes a small, legible toolset: go to a page, click, type, run a snippet of JavaScript, take a screenshot.
Where Playwright's server reads the accessibility tree, Puppeteer's takes the screenshot-first approach — the model looks at captured images and the page's text to decide what to do next. That's simpler to reason about and totally fine for light automation, though it burns more tokens and is more sensitive to layout changes on complex pages.
Worth knowing before you commit: Anthropic has archived the reference servers repository, so this server no longer receives active development. It remains genuinely useful for learning MCP, quick scraping jobs and one-off automations — the npm package still works — but for production-grade browser work the actively maintained Playwright server is the better bet. Think of Puppeteer's server as the well-worn hand tool and Playwright's as the power tool that replaced it.
The puppeteer_evaluate tool deserves a special mention: being able to run arbitrary JavaScript in the page context is a powerful escape hatch when the built-in tools don't cover an interaction.
PUPPETEER_LAUNCH_OPTIONS takes the full Puppeteer launch object, so {"headless": false, "defaultViewport": {"width": 1280, "height": 800}} lets you watch a run and pin the viewport in one setting.Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
The smallest possible surface area for understanding how an assistant drives a browser.
Grab content from client-side-rendered pages that plain HTTP fetching can't see.
Fill a form, download a report, poke at a page — without writing a script.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| puppeteer_navigate | Navigate the browser to a URL |
| puppeteer_screenshot | Capture a screenshot of the page or a specific element |
| puppeteer_click | Click an element by CSS selector |
| puppeteer_fill | Type a value into an input field |
| puppeteer_select | Choose an option in a select element |
| puppeteer_evaluate | Run arbitrary JavaScript in the page context and return the result |
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
}
}
}Node.js 18+. Downloads its own Chromium on first run.
| Variable | Description | Required |
|---|---|---|
| PUPPETEER_LAUNCH_OPTIONS | JSON launch options passed to Puppeteer (e.g. headless mode, window size)e.g. {"headless": false} | Optional |
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
W3C MCP — web-standards lookup over w3c/browser-specs (GitHub, CF-reachable).
A Model Context Protocol (MCP) server that exposes Firecrawl's API for scraping, crawling, mapping, searching, parsing documents, browser automation, and academic research.
MCP server for shufersal automation using Puppeteer
PyMuPDF compiled to WebAssembly - Full PDF manipulation in the browser