Puppeteer MCP Server

@rotexhawk

Repository

Basic information

About Puppeteer MCP Server

MCP Puppeteer Server HomeAssistant Add-on

#puppeteer #browser-automation #home-assistant

Puppeteer MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Mcp-Puppeteer-Server": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp/puppeteer",
        "-f",
        "src/puppeteer/Dockerfile",
        "."
      ]
    }
  }
}

Puppeteer MCP Server tools

Navigate to any URL in the browser

Capture screenshots of the entire page or specific elements

Click elements on the page

Hover elements on the page

Fill out input fields

Select an element with SELECT tag

Execute JavaScript in the browser console

Overview

What is Puppeteer?

Puppeteer is an MCP server that provides browser automation capabilities using Puppeteer, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

How to use Puppeteer?

You can run Puppeteer via Docker (using headless Chromium) or via NPX. Configure it in your MCP client (e.g., Claude Desktop) with the command and arguments provided in the README.

Key features of Puppeteer

Browser navigation to any URL
Screenshot capture of full page or elements
Click, hover, fill, and select on web pages
Execute arbitrary JavaScript in the browser
Monitor console logs from the browser

Use cases of Puppeteer

Automate web browsing tasks for LLM-driven workflows
Capture screenshots of web pages for analysis or record-keeping
Interact with web forms and extract data programmatically

Frequently asked questions

What is the difference between Docker and NPX usage?

The Docker implementation runs headless Chromium, while the NPX version opens a visible browser window.

What resources does Puppeteer provide?

It provides access to console logs via `console://logs` and screenshots via `screenshot://<name>` as PNG images.

What dependencies are required to run Puppeteer?

You need either Docker or Node.js with NPX installed, along with a compatible MCP client (e.g., Claude Desktop).

How are screenshots stored and accessed?

Screenshots are stored in memory and accessible via the name specified during capture using the resource URI `screenshot://<name>`.

Can Puppeteer run without a display server?

Yes, when using Docker the browser runs headless, so no display server is required.

Comments

More Browser Automation MCP servers

Scrapling MCP Server

D4Vinci

Official MCP server of the Scrapling web scraping framework: HTTP requests, stealthy browser, screenshots and network inspection for AI agents.

98.9K

Browse Bridge

Share selected Chrome tabs with AI agents. You enable the tab you want to share and maintain the ability to instantly take control. Browse Bridge is a remote MCP server available at https://mcp.browsebridge.com. What c