MCP Catalogs
HomeDrissionPageMCP screenshot

DrissionPageMCP

by wxhzhwxhzh·214·Score 46

A browser automation MCP server using DrissionPage and FastMCP for AI-controlled web operations.

browser-automationweb-scrapingdeveloper-tools
40
Forks
3
Open issues
3 mo ago
Last commit
2d ago
Indexed

Overview

DrissionPageMCP is a specialized MCP server that bridges AI capabilities with browser automation through DrissionPage library. It provides comprehensive APIs for controlling web browsers, including page navigation, element interaction, JavaScript execution, and network monitoring. The server exposes tools for browser control, file operations, and screenshot capabilities, making it particularly valuable for web scraping, automated testing, and complex web interactions that require AI decision-making.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Automated web testing with AI-based element detection
you:Web scraping with intelligent data extraction
you:AI-controlled website interaction for automation workflows
you:What browsers are supported?
you:Can this MCP server be used for web scraping?

When to choose this

Choose DrissionPageMCP when you need browser automation capabilities through MCP for AI agents, especially when working with Chinese web pages that require robust element handling.

When NOT to choose this

Avoid if you need cross-browser support beyond Chrome, or if you're working in a restricted environment where installing additional browsers isn't feasible.

Tools this server exposes

12 tools extracted from the README
  • open_browser

    Open and connect to a browser instance

  • close_browser

    Close the active browser instance

  • find_element

    Locate a page element for interaction

  • execute_javascript

    Run JavaScript code in the browser

  • screenshot

    Capture a screenshot of the current page

  • simulate_keyboard

    Simulate keyboard key presses

  • download_file

    Download files from the current page

  • upload_file

    Upload files to a webpage

  • monitor_packets

    Monitor network packets in the background

  • get_page_source

    Retrieve the HTML source of the current page

  • navigate_to

    Navigate to a specific URL

  • wait_for_element

    Wait for an element to appear on the page

Note: Tool names were inferred from the features listed in the README, as there wasn't a dedicated 'Tools' section with explicit names and descriptions. The actual API might differ slightly.

Comparable tools

playwright-mcpbrowserless-mcppuppeteer-mcpselenium-mcp

Installation

Installation

  1. Clone the repository locally
  2. Install dependencies with uv: uv install
  3. Configure your editor's MCP settings:
{
  "mcpServers": {
    "DrissionPageMCP": {
      "type": "stdio",
      "command": "uv",
      "args": ["--directory", "<path_to_repo>", "run", "main.py"]
    }
  }
}
  1. Optional: Use the MCP inspector for debugging: mcp dev <path_to_repo>/main.py

FAQ

What browsers are supported?
Chrome browser (version 90 and above recommended) is the primary supported browser.
Can this MCP server be used for web scraping?
Yes, it provides comprehensive tools for web scraping, including JavaScript execution and network monitoring capabilities.

Compare DrissionPageMCP with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.