What is Android Mcp

Android-MCP is a lightweight, open-source MCP server that facilitates interaction between AI agents and Android devices. It enables large-language-model agents to perform real-world tasks such as app navigation, UI interaction, and automated QA testing without relying on traditional computer-vision methods.

Use cases

Use cases for Android-MCP include automating app testing processes, creating AI-driven assistants for mobile applications, and enhancing user experience through automated interactions with mobile interfaces.

How to use

To use Android-MCP, clone the repository from GitHub, ensure you have Python 3.10+ and Android Studio installed, and follow the setup instructions provided in the README. After setup, you can interact with Android devices through ADB and the Accessibility API.

Key features

Key features include native Android integration for UI interaction, compatibility with any language model, a rich toolset for mobile automation, and real-time interaction with low latency between actions.

Where to use

Android-MCP can be used in various fields including mobile application testing, automated user interface interaction, and AI-driven mobile solutions across industries such as software development, quality assurance, and user experience research.

🤖 Android MCP

Android-MCP is a lightweight, open-source bridge between AI agents and Android devices. Running as an MCP server, it lets large-language-model agents perform real-world tasks such as app navigation, UI interaction and automated QA testing without relying on traditional computer-vision pipelines or preprogramed scripts.

https://github.com/user-attachments/assets/cf9a5e4e-b69f-46d4-8487-0f61a7a86d67

✨ Features

Native Android Integration
Interact with UI elements via ADB and the Android Accessibility API: launch apps, tap, swipe, input text, and read view hierarchies.
Bring Your Own LLM/VLM
Works with any language model, no fine-tuned CV model or OCR pipeline required.
Rich Toolset for Mobile Automation
Pre-built tools for gestures, keystrokes, capture, device state, shell commands execution.
Real-Time Interaction
Typical latency between actions (e.g., two taps) ranges 2-4s depending on device specs and load.

Supported Operating Systems

Android 10+

Installation

📦 Prerequisites

Python 3.10+
UIautomator2
Android Emulator/ Android Device

🏁 Getting Started

Clone the repository

   git clone https://github.com/CursorTouch/Android-MCP.git
   cd Android-MCP

Install dependencies

   uv python install 3.10
   uv sync

Connect to the MCP server
Locate your Claude Desktop configuration file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the following JSON to your Claude Desktop config:

{
  "mcpServers": {
    "android-mcp": {
      "command": "path/to/uv",
      "args": [
        "--directory",
        "path/to/Android-MCP",
        "run",
        "main.py",
        "--emulator"
      ]
    }
  }
}

Replace:

path/to/uv with the actual path to your uv executable
path/to/Android-MCP with the absolute path to where you have cloned this repo

NOTE: --emulator this is used to run in emulator, remove it to use actual device

Restart the Claude Desktop

Open your Claude Desktop, “android-mcp” should now appear as an integration.

For troubleshooting tips (log locations, common ADB issues), see the MCP docs.

🛠️ MCP Tools

Claude can access the following tools to interact with Windows:

State-Tool: To understand the state of the device.
Click-Tool: Click on the screen at the given coordinates.
Long-Click-Tool: Perform long click on the screen at the given coordinates.
Type-Tool: Type text on the specified coordinates (optionally clears existing text).
Swipe-Tool: Perform swipe from one location to other.
Drag-Tool: Drag from one point to another.
Press-Tool: To press the keys on the mobile device (Back, Volume Up, …etc).
Wait-Tool: Pause for a defined duration.
State-Tool: Combined snapshot of active apps and interactive UI elements.
Notification-Tool: To access the notifications seen on the device.
Shell-Tool: To execute shell commands on the android device.

⚠️ Caution

Android-MCP can execute arbitrary UI actions on your mobile device. Use it in controlled environments (emulators, test devices) when running untrusted prompts or agents.

🪪 License

This project is licensed under the MIT License. See LICENSE for details.

🤝 Contributing

Contributions are welcome! Please read CONTRIBUTING for dev setup and PR guidelines.

Made with ❤️ by Jeomon George

Citation

@misc{
  author       = {Jeomon George},
  title        = {Android-MCP},
  year         = {2025},
  publisher    = {GitHub},
  howpublished = {\url{https://github.com/CursorTouch/Android-MCP}},
  note         = {Lightweight open-source bridge between LLM agents and Android},
}

Android Mcp

Overview