playwright-universal-mcp

playwright-universal-mcp

3.1

If you are the rightful owner of playwright-universal-mcp 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.

Playwright Universal MCP is a server for browser automation that supports multiple browsers and works in containerized environments.

Playwright Universal MCP is a versatile Model Context Protocol (MCP) server designed for browser automation. It supports multiple browsers including Chromium, Chrome, Microsoft Edge, Firefox, and WebKit, making it a flexible choice for various automation needs. The server is particularly suited for containerized environments with limited privileges, such as Docker containers, ensuring reliable performance even in constrained settings. It offers both headless and headful modes, allowing users to run browsers without a GUI for server environments or with a GUI for debugging purposes. The server provides extensive browser control capabilities, enabling users to navigate, click, type, take screenshots, and manage multiple pages or tabs. This makes it an ideal tool for AI assistants like Claude and GPT-4, which require robust browser interaction capabilities.

Features

  • Multi-browser support: Choose between Chromium, Chrome, Microsoft Edge, Firefox, or WebKit.
  • Container-friendly: Works in environments with limited privileges, such as Docker containers.
  • Headless/Headful modes: Run in headless mode for server environments or headful mode for debugging.
  • Extensive browser control: Navigate, click, type, take screenshots, and more.
  • Multiple page support: Create and manage multiple browser pages or tabs.

Tools

  1. navigate

    Navigate to a URL.

  2. click

    Click on an element by selector or text.

  3. type

    Type text into an input element.

  4. get_text

    Get text content from an element.

  5. get_page_content

    Get the current page HTML content.

  6. take_screenshot

    Take a screenshot of the current page.

  7. new_page

    Create a new browser page.

  8. switch_page

    Switch to a different browser page.

  9. get_pages

    List all available browser pages.

  10. wait_for_selector

    Wait for an element to be visible on the page.

  11. get_browser_info

    Get information about the current browser session.