mcp server cloudbrowser

Local 2025-09-01 00:15:08 0
Browser Automation @clpublic/mcp-server-cloudbrowser

The Yunlogin MCP Browser Service provides the capability of automated access to cloud browsers. This service enables the Large Language Model (LLM) to automatically execute browser interactions (such as accessing web pages, taking screenshots of pages or specific elements, extracting data, filling out forms, etc.) within the environment of an anti-association fingerprint cloud browser, achieving traceless cloud-based automation.

Test

  1. Run npm install to install the necessary dependencies, then run npm run build to get dist/index.js.
  2. Run npm run inspector to start the server.

Get Started

  1. Run npm install to install the necessary dependencies, then run npm run build to get dist/index.js.

  2. Set up your Claude Desktop configuration to use the server.

{
  "mcpServers": {
    "cloudbrowser": {
      "command": "node",
      "args": ["path/to/mcp-server-cloudbrowser/cloudbrowser/dist/index.js"],
      "env": {
        "API_KEY": "<YOUR_BROWSERBASE_API_KEY>"
      }
    }
  }
}

  1. Restart your Claude Desktop app and you should see the tools available clicking the ? icon.

  2. Start using the tools! Below is an image of Claude closing a browser session.

Tools

Browserbase API

  • cloudbrowser_navigate

  • Navigate to any URL in the browser

  • Input: url (string)

  • cloudbrowser_evaluate

  • Execute JavaScript in the browser console

  • Input: script (string): JavaScript code to execute

  • cloudbrowser_get_current_url

  • Retrieve the current URL of the browser page

  • cloudbrowser_screenshot

  • Capture screenshots of the entire page or specific elements

  • Inputs:

    • name (string, required): Name for the screenshot
    • selector (string, optional): CSS selector for element to screenshot
    • width (number, optional, default: 800): Screenshot width
    • height (number, optional, default: 600): Screenshot height

  • cloudbrowser_click

  • Click elements on the page

  • Input: selector (string): CSS selector for element to click

  • cloudbrowser_fill

  • Fill out input fields

  • Inputs:

    • selector (string): CSS selector for input field
    • value (string): Value to fill

  • cloudbrowser_get_text

  • Extract all content from the current page

  • Input: selector (string, optional): CSS selector to get content from specific elements

Resources

The server provides access to two types of resources:

  1. Screenshots (screenshot://<name>)
  2. PNG images of captured screenshots
  3. Accessible via the screenshot name specified during capture