Android-MCP

Android-MCP

3.4

If you are the rightful owner of Android-MCP and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Android-MCP is a lightweight, open-source bridge between AI agents and Android devices, enabling real-world task automation without traditional computer-vision pipelines.

Android-MCP serves as a model context protocol server that facilitates interaction between large-language-model (LLM) agents and Android devices. It allows AI agents to perform tasks such as app navigation, UI interaction, and automated QA testing. By leveraging the Android Accessibility API and ADB, Android-MCP provides a seamless integration with Android devices, enabling real-time interaction with typical latency between actions ranging from 2-4 seconds. This server is designed to work with any language model, eliminating the need for fine-tuned computer vision models or OCR pipelines. Android-MCP is compatible with Android 10+ and requires Python 3.10+ and UIautomator2 for installation. It is particularly useful for developers and testers who need to automate mobile tasks in a controlled environment, such as emulators or test devices.

Features

  • Native Android Integration: Interact with UI elements via ADB and the Android Accessibility API.
  • Bring Your Own LLM/VLM: Compatible with any language model without requiring fine-tuned CV models.
  • Rich Toolset for Mobile Automation: Includes pre-built tools for gestures, keystrokes, and device state management.
  • Real-Time Interaction: Provides low-latency interaction between actions.
  • Supports Android 10+: Compatible with modern Android operating systems.

Tools

  1. State-Tool

    To understand the state of the device.

  2. Click-Tool

    Click on the screen at the given coordinates.

  3. Long-Click-Tool

    Perform long click on the screen at the given coordinates.

  4. Type-Tool

    Type text on the specified coordinates (optionally clears existing text).

  5. Swipe-Tool

    Perform swipe from one location to another.

  6. Drag-Tool

    Drag from one point to another.

  7. Press-Tool

    To press the keys on the mobile device (Back, Volume Up, ...etc).

  8. Wait-Tool

    Pause for a defined duration.

  9. Notification-Tool

    To access the notifications seen on the device.

  10. Shell-Tool

    To execute shell commands on the android device.