mcp-puppeteer

mcp-puppeteer

3.1

If you are the rightful owner of mcp-puppeteer and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol server that provides browser automation capabilities using Puppeteer.

The Puppeteer MCP server enables Language Model Models (LLMs) to interact with web pages in a real browser environment. It allows for browser automation, including navigation, clicking, form filling, and JavaScript execution. This server is particularly useful for tasks that require interaction with web pages, such as taking screenshots or monitoring console logs. By leveraging Puppeteer, the server can perform complex web interactions, making it a powerful tool for developers and researchers working with LLMs. The server supports both Docker and NPX configurations, providing flexibility in deployment. It is licensed under the MIT License, allowing for free use, modification, and distribution.

Features

  • Browser automation
  • Console log monitoring
  • Screenshot capabilities
  • JavaScript execution
  • Basic web interaction (navigation, clicking, form filling)

Tools

  1. puppeteer_navigate

    Navigate to the specified URL

  2. puppeteer_screenshot

    Capture screenshots of pages or elements

  3. puppeteer_click

    Click on the element on the page

  4. puppeteer_hover

    Elements hovering on the page

  5. puppeteer_fill

    Fill in the form field

  6. puppeteer_select

    Select the drop-down menu option

  7. puppeteer_evaluate

    Execute JavaScript in the browser console