Mobitru MCP Server

Main Features

• 🚀 Fast and lightweight: Uses native accessibility trees for most in## Installation and Configuration

Setup Mobitru MCP Server with Cursor, Claude, VS Code, GitHub Copilot:

Mobile Server

{
  "mcpServers": {
    "mobitru-mobile": {
      "command": "npx",
      "args": ["-y", "mobitru-mcp-server", "mobile"]
    }
  }
}

Playwright Server

{
  "mcpServers": {
    "mobitru-playwright": {
      "command": "npx",
      "args": ["-y", "mobitru-mcp-server", "playwright"]
    }
  }
}

Claude Desktop Configuration

For mobile automation:

claude mcp add mobitru-mobile -- npx -y mobitru-mcp-server mobile

For web/browser automation:

claude mcp add mobitru-playwright -- npx -y mobitru-mcp-server playwright

• 🤖 LLM-friendly: No computer vision model required in Accessibility (Snapshot).
• 🧿 Visual Sense: Evaluates and analyses what's actually rendered on screen to decide the next action. If accessibility data or view-hierarchy coordinates are unavailable, it falls back to screenshot-based analysis.
• 📊 Deterministic tool application: Reduces ambiguity found in purely screenshot-based approaches by relying on structured data whenever possible.
• 📺 Extract structured data: Enables you to extract structured data from anything visible on screen.
• 🧪 Test Execution: Run Appium (mobile) and Playwright (web) test scripts directly on Mobitru cloud infrastructure.

Benefits

• ✅ Real device testing without local setup
• ✅ Parallel execution across multiple devices/browsers
• ✅ Built-in video recording and artifacts
• ✅ Cross-platform compatibility testing and Automation

This is a Model Context Protocol (MCP) server that enables scalable mobile automation and development through Mobitru's cloud platform. This server allows Agents and LLMs to interact with native iOS/Android applications, desktop browsers, and mobile devices through structured accessibility snapshots or coordinate-based taps based on screenshots.