CloudBrowser MCP Server

An MCP server implementation that provides tools for controlling remote cloud browsers through CloudBrowser.ai with AI-powered automation capabilities.

Features

• Remote Browser Management: Open, close, and control cloud browsers
• Direct Browser Control: Puppeteer-based automation via Chrome DevTools Protocol
• Session Management: Save and restore browser sessions with cookies/localStorage
• Remote Desktop Access: Integration for visual browser control
• AI-Powered Automation: Intelligent page content analysis and element interaction
• Dual Transport: Support for both stdio and HTTP communication

Configuration

Prerequisites

You need a CloudBrowser.ai API token. Get one from CloudBrowser.ai.

Usage with OpenAI Agents, n8n, and Make (HTTP method)

For OpenAI Agents, n8n, and Make integrations, use the HTTP endpoint:

• Endpoint: https://mcp.cloudbrowser.ai
• Authorization Header: Bearer your_api_token_here

Usage with Claude Desktop (STDIO method)

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "cloudbrowser": {
      "command": "npx",
      "args": ["@cloudbrowser/mcp-server"],
      "env": {
        "CLOUDBROWSER_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

MCP Tools list

Browser Management

• open_browser - Opens a new remote browser instance in the cloud
• close_browser - Closes a specific browser instance
• get_browsers - Lists all active browser instances
• start_remote_desktop - Starts VNC access to a browser
• stop_remote_desktop - Stops VNC access to a browser
• get_saved_sessions - Lists saved browser sessions
• remove_saved_session - Removes a saved session

Browser Automation

• connect_to_browser - Establishes direct control connection to a browser
• navigate_to_url - Navigates to a specific URL
• get_page_content - Extracts comprehensive page content and structure
• click_element - Clicks on page elements using CSS selectors
• type_text - Types text into form fields and inputs
• get_elements - Gets information about elements matching a selector
• take_screenshot - Captures page screenshots
• evaluate_script - Executes JavaScript code on the page
• detect_captcha - Detects captcha widgets in current page
• solve_captcha - Solves captcha via CloudBrowserPublicApi /solve and injects token

License

MIT

Captcha Resolution Integration (CloudBrowserPublicApi)

This MCP resolves captchas through CloudBrowserPublicApi (/solve). The MCP does not call the captcha solver service directly.

Configure these env vars in the MCP deployment:

env:
  - name: CLOUDBROWSER_PUBLICAPI_BASE_URL
    value: "http://cloudbrowserpublicapi.browsers.svc.cluster.local"
  - name: CLOUDBROWSER_PUBLICAPI_API_KEY
    valueFrom:
      secretKeyRef:
        name: cloudbrowserpublicapi-secret
        key: api-key
  - name: CLOUDBROWSER_PUBLICAPI_SOLVE_PATH
    value: "/solve"
  - name: CLOUDBROWSER_PUBLICAPI_TIMEOUT_MS
    value: "120000"
  - name: CAPTCHA_AUTO_SOLVE
    value: "true"

Production interaction flow

1. open_browser
2. connect_to_browser
3. navigate_to_url with autoSolveCaptcha: true (or call detect_captcha and solve_captcha manually)
4. Continue with normal actions (click_element, type_text, etc.)

Example tools/call for automatic solve:

{
  "jsonrpc": "2.0",
  "id": 7,
  "method": "tools/call",
  "params": {
    "name": "navigate_to_url",
    "arguments": {
      "sessionId": "my-session",
      "url": "https://example.com/login",
      "autoSolveCaptcha": true,
      "detectCaptcha": true
    }
  }
}