Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_emulators | List all available Android emulators and devices with their name, ID, status, and dimensions |
| take_screenshot | Take a screenshot for the specified device/emulator. If no device_id is provided, uses the default device. Set annotate_elements=False to take a plain screenshot without UI element annotations. |
| press | Tap on specific coordinates on the Android screen. Use duration for long press (in milliseconds). |
| long_press | Long press on specific coordinates on the Android screen. |
| get_ui_elements_info | Get detailed information about all interactive UI elements on the screen including their coordinates and properties. |
| get_device_dimensions | Get the dimensions of the Android device/emulator screen. |
| press_back | Press the hardware back button on the Android device/emulator. |
| swipe | Swipe horizontally or vertically on the Android screen. Args:
direction: 'left', 'right', 'up', 'down' for directional swipes
x1, y1, x2, y2: Exact coordinates for custom swipes
device_id: Optional device ID to target specific device/emulator
distance: Distance of swipe in pixels (default: 50% of screen dimension)
duration: Duration of swipe in milliseconds (default: 300ms) |
| type_text | Type text into the currently focused input field on the Android device/emulator. Args:
text: The text to type into the input field
device_id: Optional device ID to target specific device/emulator
clear_first: If True, clears existing text before typing new text |
| scroll_element | Scroll a specific UI element in the given direction for a specified distance. Args:
element: Either an integer (element index from annotated screenshot) or string (element name)
direction: Direction to scroll - 'up', 'down', 'left', 'right'
distance: Distance to scroll in pixels (default: 200)
duration: Duration of scroll gesture in milliseconds (default: 300)
device_id: Optional device ID to target specific device/emulator |
| record_video | Start recording a video using scrcpy. The video will be saved to the videos directory. |
| stop_video | Stop the active video recording for the specified device. |