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 |
|---|---|
| initialize-appium | Initialize an Appium driver session for mobile automation |
| close-appium | Close the current Appium driver session |
| appium-screenshot | Take a screenshot using Appium |
| tap-element | Tap on a UI element identified by a selector |
| send-keys | Send text input to a UI element |
| get-page-source | Get the XML representation of the current UI |
| swipe | Perform a swipe gesture on the screen |
| wait-for-element | Wait for an element to be visible on screen |
| long-press | Perform a long press gesture on an element |
| scroll-to-element | Scroll until an element becomes visible |
| get-orientation | Get the current device orientation |
| set-orientation | Set the device orientation |
| hide-keyboard | Hide the keyboard if it's currently visible |
| get-current-package | Get the current active app package name |
| get-current-activity | Get the current Android activity name |
| launch-appium-app | Launch the app associated with the current Appium session |
| close-app | Close the app associated with the current Appium session |
| reset-app | Reset the app (terminate and relaunch) associated with the current Appium session |
| get-device-time | Get the current device time |
| lock-device | Lock the device screen |
| is-device-locked | Check if the device is currently locked |
| unlock-device | Unlock the device screen |
| press-key-code | Press an Android key code |
| open-notifications | Open the notifications panel (Android only) |
| get-contexts | Get all available contexts (NATIVE_APP, WEBVIEW, etc.) |
| switch-context | Switch between contexts (e.g., NATIVE_APP, WEBVIEW) |
| get-current-context | Get the current context |
| pull-file | Pull a file from the device |
| push-file | Push a file to the device |
| get-battery-info | Get the device battery information |
| element-exists | Check if an element exists on the current page |
| list-ios-simulators | Get list of available iOS simulators |
| find-by-ios-predicate | Find an element using iOS predicate string (iOS only) |
| find-by-ios-class-chain | Find an element using iOS class chain (iOS only) |
| tap-by-ios-predicate | Tap on an element using iOS predicate string (iOS only) |
| tap-by-ios-class-chain | Tap on an element using iOS class chain (iOS only) |
| send-keys-by-ios-predicate | Send text to an element using iOS predicate string (iOS only) |
| send-keys-by-ios-class-chain | Send text to an element using iOS class chain (iOS only) |
| perform-touch-id | Simulate Touch ID fingerprint (iOS only) |
| shake-device | Simulate shake gesture (iOS only) |
| start-recording | Start recording the screen |
| stop-recording | Stop recording the screen and get the recording data |
| execute-mobile-command | Execute a custom mobile command for iOS or Android |
| get-element-text | Get text content from a UI element |
| send-keys-to-device | Send keys directly to the device without focusing on any element |
| send-key-event | Send a key event to the device (e.g., HOME, BACK) |
| clear-element | Clear text from an input element |
| scroll-screen | Scroll the screen in a specified direction |
| get-element-attributes | Get all available attributes of an element |
| inspect-element | Get detailed information about an element (for debugging) |
| get-element-tree | Get a hierarchical view of the UI elements (similar to Appium Inspector) |
| has-text-in-screen | Check if specific text exists anywhere on the current screen |
| find-elements-by-text | Find all elements containing specific text |
| tap-element-by-text | Tap on an element containing specific text |
| generate-element-locators | Generate multiple types of locators for an element |
| perform-element-action | Perform a specific action on an element using various locator strategies |
| smart-tap | Intelligently tap an element trying different locator strategies in a specific order |
| inspect-and-tap | Inspect an element using one locator, then tap using the best available locator |
| perform-w3c-gesture | Perform touch gestures using the W3C Actions API (more reliable than TouchAction API) |
| extract-locators | Extract element locators from UI XML source |
| save-ui-hierarchy | Save UI hierarchy XML to a file |
| find-by-text | Generate XPath to find element by text |
| generate-test-script | Generate Appium test script from actions |
| inspect-and-act | Inspect UI to identify element locators and then perform an action |
| capture-ui-locators | Capture all UI elements and their locators for future use |
| list-devices | List all connected Android devices |
| install-app | Install an Android application APK |
| uninstall-app | Uninstall an Android application |
| take-screenshot | Take a screenshot on an Android device |
| list-installed-packages | List all installed packages on an Android device |
| launch-app | Launch an app on an Android device |
| execute-adb-command | Execute a custom ADB command |
| xcode_check_cli_installed | Check if Xcode command line tools are installed |
| xcode_get_path | Get the path to the Xcode installation |
| xcode_install_cli | Install Xcode command line tools (requires user interaction) |
| xcode_get_ios_simulators | Get a list of available iOS simulators |
| xcode_boot_simulator | Boot an iOS simulator |
| xcode_shutdown_simulator | Shutdown an iOS simulator |
| xcode_create_simulator | Create a new iOS simulator |
| xcode_delete_simulator | Delete an iOS simulator |
| xcode_erase_simulator | Erase all data from a simulator |
| xcode_get_simulator_status | Get the status of all simulators |
| xcode_get_simulator_info | Get detailed information about a specific simulator |
| xcode_wait_for_simulator | Wait for a simulator to be ready |
| xcode_install_app | Install an app on a simulator |
| xcode_uninstall_app | Uninstall an app from a simulator |
| xcode_launch_app | Launch an app on a simulator |
| xcode_terminate_app | Terminate an app on a simulator |
| xcode_list_installed_apps | List all installed apps on a simulator |
| xcode_take_screenshot | Take a screenshot of a simulator |
| xcode_record_video | Start recording video of a simulator (returns process info) |
| xcode_add_media_to_simulator | Add photos/videos to a simulator |
| xcode_copy_to_simulator | Copy files to a simulator (limited to media files) |
| xcode_get_privacy_permission | Get privacy permission status for an app |
| xcode_grant_privacy_permission | Grant privacy permission to an app |
| xcode_revoke_privacy_permission | Revoke privacy permission from an app |
| xcode_reset_privacy_permission | Reset privacy permission for an app |
| xcode_open_url | Open a URL on a simulator |
| xcode_set_simulator_location | Set the location of a simulator |
| xcode_clear_simulator_location | Clear the location of a simulator |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |