Android-MCP is a lightweight, open-source tool that bridge between AI agents and Android devices. Running as an MCP server, it lets LLM 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.
**KEY FEATURES**
- **Native Android Integration**: Interact with UI elements via ADB and the Android Accessibility API.
- **Bring Your Own LLM/VLM**: Works with any language model.
- **Rich Toolset for Mobile Automation**: Pre-built tools for gestures, keystrokes, capture, device state, etc.
- **Real-Time Interaction**: Typical latency between actions ranges 2-4s.
**MINIMUM REQUIREMENTS**
- Python 3.13 or higher
- Android Debug Bridge (ADB)
Ensure ADB is installed and your device is connected/authorized.
- UV Package Manager
This MCP server requires UV, a fast Python package manager.
Installation:
`curl -LsSf https://astral.sh/uv/install.sh | sh`
For detailed installation instructions, [see the UV documentation](https://github.com/astral-sh/uv)
Tools
- Click
- Snapshot
- LongClick
- Swipe
- Type
- Drag
- Press
- Notification
- Wait
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won’t change.