🤖 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

✨ Key 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 (Vision Optional) 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.

• Real-Time Interaction Typical latency between actions (e.g., two taps) ranges 2 – 5 s depending on device specs and load.

Supported Operating Systems

• Android 10+

Installation

Prerequisites

• Python 3.10+
• Android Studio

🏁 Getting Started

1. Clone the repository

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

2. Install dependencies

   uv pip install -r pyproject.toml

3. Connect to the MCP server

Add the following JSON (replace {{PATH}} placeholders) to your client config:

   {
     "mcpServers": {
       "android-mcp": {
         "command": "{{PATH_TO_UV}}",
         "args": [
           "--directory",
           "{{PATH_TO_SRC}}/Android-MCP",
           "run",
           "main.py"
         ]
       }
     }
   }

For Claude Desktop, save as %APPDATA%/Claude/claude_desktop_config.json.

4. Enable ADB & authorize your device

   adb devices   # verify that your phone/tablet appears and is "authorized"

5. 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.

⚠️ 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},
}