Skip to main content
MCP Server
Puppeteer avatar

Puppeteer

by @modelcontextprotocol

Official Install with VS Code GitHub

Browser automation and web scraping

Share
puppeteerbrowserautomationscrapingscreenshotchrome
1,100 stars TypeScript MIT Updated: 2025-04-25

Send to Your Agent

Copy this prompt and paste it into Claude, Cursor, or any MCP client to install instantly.

Install the Puppeteer MCP server for me.

Server: Puppeteer
Description: Browser automation and web scraping
Install command: npx -y @modelcontextprotocol/server-puppeteer

GitHub: https://github.com/modelcontextprotocol/servers-archived/tree/main/src/puppeteer

Please install this MCP server and confirm when ready.

Paste into any AI agent with MCP support — works with Claude Desktop, Cursor, Cline, and more.

Quick Install

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json

  1. Open Claude Desktop app
  2. Go to Settings → Developer → Edit Config
  3. Paste the config below into the file
  4. Restart Claude Desktop
{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-puppeteer"
      ]
    }
  }
}

Add this to your ~/Library/Application Support/Claude/claude_desktop_config.json

Installation Methods

npx Run directly with npx
npx -y @modelcontextprotocol/server-puppeteer

Tools (7)

navigate

Navigate to a URL in the browser

screenshot

Take a screenshot of the current page

click

Click an element on the page

type

Type text into an input field

get_content

Get the HTML content of the current page

evaluate

Execute JavaScript in the browser context

close

Close the browser

Compatibility

Claude Desktop
Cursor
Cline
VS Code
Devin (formerly Windsurf)

About

A Model Context Protocol server that provides browser automation capabilities using Puppeteer. This server enables LLMs to control a headless Chrome browser for web scraping, testing, and automation.

Key Features

  • Page navigation — Visit URLs and wait for page loads
  • Screenshots — Capture visual renders of web pages
  • Element interaction — Click, type, and interact with page elements
  • Content extraction — Get HTML, text, or execute JavaScript
  • Form automation — Fill out and submit forms

Requirements

Requires a Chromium/Chrome installation. The server will attempt to find Chrome automatically, or you can specify the path via the PUPPETEER_EXECUTABLE_PATH environment variable.

Use Cases

  • Visual testing — "Take a screenshot of this page and check the layout"
  • Form automation — "Fill out this contact form and submit it"
  • Content extraction — "Get the article content from this paywalled site"
  • Web scraping — "Extract all product prices from this e-commerce page"
  • UI verification — "Verify that the login button is visible and clickable"

Related Resources

Browser Use

MCP Server

Browse the web, directly from Cursor etc.

MCP Tool Orchestrator

Prompt

Design and orchestrate complex multi-tool workflows using the Model Context Protocol (MCP). Build intelligent agent systems that coordinate multiple MCP servers for sophisticated automation tasks.

AutoGPT Agent Operator

Skill

Deploy and manage autonomous AI agents using AutoGPT for complex, multi-step task completion.

Artificial Intelligence

Glossary

The broad field of creating machines that can perform tasks requiring human-like intelligence, such as reasoning, learning, and perception.

Firecrawl

MCP Server

Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

Compare LLM Pricing

This server works with Claude, GPT-4o, and other models. Compare API costs side-by-side to find the cheapest option for your workflow.

Browse Pricing Compare Models Cost Calculator