DrissionPage MCP Server Modified

You can run and connect to the DrissionPage MCP Server to automate Chromium-based browsers through the MCP protocol, enabling AI assistants to control navigation, interact with page elements, capture screenshots, and analyze DOM structure with high performance.

How to use

You use an MCP client to talk to the DrissionPage MCP Server. Start by launching the local MCP service in STDIO mode, then configure your MCP client to point at this local server. From there you can connect to a browser, navigate pages, interact with elements, take screenshots, and read page text or DOM structure. All actions are exposed as MCP endpoints so your AI assistant can orchestrate complex browser automation tasks.

How to install

Prerequisites: you need Python to run the server and a compatible shell to install dependencies.

Clone the project to your local environment.

Install and set up the Python virtual environment, then install dependencies. The exact steps shown here use a Windows-style path example for the virtual environment.

# Clone the project
git clone https://github.com/YourUsername/DrissionPageMCPServer_Modified.git
cd DrissionPageMCPServer_Modified/

# Use uv sync for the synchronous environment
uv sync

Run the MCP server and connect your client

Start the MCP service in STDIO mode to expose the browser automation capabilities via MCP.

drissionpage-mcp

Configure your MCP client example

Configure your MCP client to load the server configuration. The following example shows how to register a local stdio server that runs through a Python interpreter inside a virtual environment.

{
  "mcpServers": {
    "drissionpage_mcp": {
      "type": "stdio",
      "name": "drissionpage_mcp",
      "command": "<YOUR_PATH>\\DrissionPageMCPServer_Modified\\.venv\\Scripts\\python.exe",
      "args": ["-m", "drissionpage_mcp.main"],
      "env": {
        "PYTHONPATH": "<YOUR_PATH>\\DrissionPageMCPServer_Modified\\src"
      }
    }
  }
}

Available tools

connect_browser

Connect to or start a browser session to enable subsequent automation tasks

new_tab

Open a new browser tab for isolated interactions

navigate

Navigate the current tab to a specified URL

click_element

Click a page element identified by a selector

input_text

Enter text into an input field identified by a selector

get_element_text

Retrieve text content from a specified element

get_page_text

Extract all visible text from the current page

take_screenshot

Capture a screenshot of the current page or a specific element

get_screenshot_data

Return raw image data for a captured screenshot

get_dom_tree

Obtain the DOM tree of the current page for analysis

find_elements

Find multiple elements matching a selector or criteria

enable_network_monitoring

Enable capturing network activity during page interactions

get_network_logs

Retrieve captured network logs during the session

save_page_source

Save the current page's HTML source to a file

get_cookies

Retrieve cookies from the current page or session

execute_javascript

Run JavaScript in the context of the page and return results

run_cdp_command

Execute a raw CDP command to interact with the browser