Puppeteer

Provides browser automation, page interaction, and screenshot capabilities via a Puppeteer-based MCP server.

javascript

1

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rotexhawk-mcp-puppeteer-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--init",
        "-e",
        "DOCKER_CONTAINER=true",
        "mcp/puppeteer"
      ],
      "env": {
        "DOCKER_CONTAINER": "true"
      }
    }
  }
}

You can use the Puppeteer MCP Server to automate a real browser from your MCP client. It lets you navigate pages, take screenshots, interact with elements, run JavaScript in the page, and capture console logs for debugging. This makes it easy to build workflows that rely on live web pages, such as testing, data extraction, or automated browsing tasks.

How to use

To use the Puppeteer MCP Server, start it locally or via a remote MCP endpoint and connect your MCP client. Once connected, you can run a sequence of tools to drive a browser session: navigate to a URL, click or hover elements, fill forms, select options, evaluate scripts, and capture screenshots. You can also monitor the browser console output to debug scripts and verify that your interactions are performing as expected.

How to install

Prerequisites: ensure you have a compatible runtime environment installed, including Docker and Node with npm. You will run either a Docker container or an NPX command to start the server.

{
  "mcpServers": {
    "puppeteer": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--init", "-e", "DOCKER_CONTAINER=true", "mcp/puppeteer"]
    },
    "puppeteer_npx": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-puppeteer"]
    }
  }
}

Additional sections

Configuration notes: The server exposes two MCP entry points, one running in Docker and one as an NPX-based local command. Use the Docker-based approach when you want headless Chromium inside a container. Use the NPX approach for a quick, local browser instance without containerization.

Available tools

puppeteer_navigate

Navigate to a URL in the browser session. Input: url (string)

puppeteer_screenshot

Capture screenshots of the entire page or a specific element. Inputs: name (string, required), selector (string, optional), width (number, optional, default 800), height (number, optional, default 600)

puppeteer_click

Click elements on the page. Input: selector (string)

puppeteer_hover

Hover elements on the page. Input: selector (string)

puppeteer_fill

Fill input fields. Inputs: selector (string), value (string)

puppeteer_select

Select an option in a SELECT element. Inputs: selector (string), value (string)

puppeteer_evaluate

Execute JavaScript in the browser console. Input: script (string)