Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_devices | List all connected Android devices/emulators and iOS simulators |
| set_device | Select which device to use for subsequent commands |
| screenshot | Take a screenshot of the device screen. Returns base64 encoded PNG image. |
| get_ui | Get the current UI hierarchy (accessibility tree). Shows all interactive elements with their text, IDs, and coordinates. Note: Limited on iOS. |
| tap | Tap at specific coordinates or find an element by text/id and tap it |
| long_press | Long press at coordinates or on an element |
| swipe | Perform a swipe gesture |
| input_text | Type text into the currently focused input field |
| press_key | Press a key button. Android: BACK, HOME, ENTER, etc. iOS: HOME, VOLUME_UP, VOLUME_DOWN |
| find_element | Find UI elements by text, resource ID, or other criteria (Android only) |
| launch_app | Launch an app by package name (Android) or bundle ID (iOS) |
| stop_app | Force stop an app |
| install_app | Install an app. APK for Android, .app bundle for iOS simulator |
| get_current_activity | Get the currently active app/activity (Android only) |
| shell | Execute shell command. ADB shell for Android, simctl for iOS |
| wait | Wait for specified duration |
| open_url | Open URL in device browser (iOS simulator only) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |