Android Mobile MCP

Android Mobile MCP

erichung9060

Enables AI agents to control Android devices through touch, swipe, text input, and app management via ADB connection. Takes screenshots and extracts UI elements for automated mobile testing and interaction.

4217 views4Local (stdio)

What it does

  • Take screenshots of Android device screens
  • Click and swipe on specific screen coordinates
  • Extract UI elements and their hierarchical structure
  • Type text into focused input fields
  • Launch and manage Android applications
  • Press system buttons like back, home, and recent

Best for

Mobile app testing and QA automationAndroid device automation workflowsAI agents that need to interact with mobile apps
Works via ADB connectionHierarchical UI element detectionCoordinate validation prevents invalid clicks

Tools (9)

mobile_init

Initialize the Android device connection. Must be called before using any other mobile tools.

mobile_dump_ui

Get UI elements from Android screen as JSON with hierarchical structure. Returns a JSON structure where elements contain their child elements, showing parent-child relationships. Only includes focusable elements or elements with text/content_desc/hint attributes.

mobile_click

Click on a specific coordinate on the Android screen. Args: x: X coordinate to click y: Y coordinate to click

mobile_type

Input text into the currently focused text field on Android. Args: text: The text to input submit: Whether to submit text (press Enter key) after typing

mobile_key_press

Press a physical or virtual button on the Android device. Args: button: Button name (BACK, HOME, RECENT, ENTER)

Alternatives