MCP Appium
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANDROID_HOME | No | Path to the Android SDK installation | |
| SCREENSHOTS_DIR | No | Directory path where screenshots are saved. Supports both absolute and relative paths (relative paths are resolved from the current working directory). The directory is created automatically if it doesn't exist. If not set, screenshots are saved to the current working directory. | |
| CAPABILITIES_CONFIG | No | Path to the capabilities.json configuration file that defines device capabilities for Android and iOS |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| logging | {} |
| resources | {
"subscribe": true,
"listChanged": true
} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| select_deviceA | Discover/select a LOCAL device. Ask for platform if unknown; one device is auto-selected. For multiple devices, ask the user to choose, then pass deviceUdid. Next: prepare_ios_simulator for iOS simulators, then appium_session_management action=create. Skip for REMOTE servers: pass device capabilities (appium:deviceName/appium:udid) and the user-provided remoteServerUrl to session creation. |
| appium_session_managementA | Manage Appium sessions. Use action=create to start a session, attach to connect to an existing one, detach to forget an attached session, delete to stop one, list to see all active sessions, or select to switch the active session. |
| appium_mobile_device_controlA | Control device behavior: lock/unlock the screen, shake the device, or open the notifications panel. Use the action parameter to choose what to do. |
| appium_geolocationA | Get, set, or reset the device geolocation (GPS coordinates). Works on both iOS (simulators and real devices) and Android (emulators and real devices with mock location enabled). Use action=get to read current coordinates, action=set with latitude/longitude (and optional altitude for Android) to simulate a location, or action=reset to restore the system default. Note: On Android emulators, reset is not supported — use action=set to manually restore coordinates instead. On Android real devices, the mocked location may persist until the GPS cache refreshes. |
| appium_mobile_device_infoA | Get device information, battery status, or current device time in a single call. Use the "action" parameter to select which data to retrieve. Works on both iOS and Android. |
| appium_mobile_fileA | Push or pull a file using Appium mobile extensions. action=push uses payloadBase64, action=pull returns contentBase64. |
| appium_driver_settingsA | Read or update Appium driver session settings (e.g. idle timeouts, selector waits). Use action=get to return JSON settings; action=update merges a map into the session. Works for embedded UiAutomator2/XCUITest sessions and remote WebDriver clients that support Appium settings. |
| prepare_ios_simulatorA | Boot an iOS/tvOS simulator, download/cache WDA, and launch it on a free per-simulator port. Pass capabilitiesHint (appium:webDriverAgentUrl) to appium_session_management action=create to reuse WDA. skipWda=true only boots. APPIUM_MCP_WDA_APP_PATH can point to an extracted WebDriverAgentRunner-Runner.app (absolute path) to skip download. |
| appium_prepare_ios_real_deviceA | Prepare signed WDA for a real iOS device. Omit provisioningProfileUuid to list profiles; ask the user to choose, highlighting recommendedForWda. Pass the chosen UUID to download, package, and sign WDA; wildcard profiles use a concrete WDA bundle ID. Downloads/unsigned IPA are cached per version; signing always reruns. Pass capabilitiesHint to appium_session_management action=create to install/launch the signed WDA. Requires macOS, Xcode 16+, and a paired developer-mode device. |
| appium_gestureA | Perform a touch gesture. Use 'action' to choose: tap, double_tap, long_press, scroll, swipe, pinch_zoom, scroll_to_element, back. Choose scroll vs swipe by intent: scroll to browse content in a list or feed; swipe to dismiss, switch screens, navigate carousels, or pull-to-refresh (speed=fast). For drag-and-drop use appium_drag_and_drop. For custom multi-touch use appium_perform_actions. |
| appium_drag_and_dropA | Perform a drag-and-drop gesture from a source location to a target location. The gesture: long press the source (default 600ms), drag to the target (default 1200ms), then release. Source and target can each be specified as either an element UUID or coordinates. Useful for reordering lists, moving items, drag-to-delete. |
| appium_perform_actionsA | Execute raw W3C Actions API sequences for advanced multi-touch gestures not covered by appium_gesture. Use this for custom multi-finger gestures (rotate, three-finger swipe, edge swipes), complex timing sequences, or any gesture requiring precise control over individual touch points. Prefer appium_gesture for standard gestures (tap, scroll, swipe, pinch) — it handles platform differences automatically. |
| appium_find_elementA | Find an element by strategy and selector; the primary tool for locating a specific target. Returns its ID for interactions. Pass that ID as elementUUID to interaction tools. Prefer accessibility id > id > platform-native > xpath (last resort: slow/brittle). See strategy for platform-specific guidance. To scroll until a target is found, use appium_gesture action=scroll_to_element with the same strategy and selector, rather than repeatedly calling this tool. For natural-language/vision finding, use appium_ai action=find_element if enabled and stable locators do not work. |
| appium_mobile_press_keyA | Press navigation keys (BACK, HOME, APP_SWITCH) on Android or physical buttons (HOME, volume, etc.) on iOS/tvOS. |
| appium_set_valueB | Enter text into an element |
| appium_mobile_keyboardA | Hide the software keyboard or check if it is visible (Android UiAutomator2 / iOS XCUITest). action=hide uses mobile: hideKeyboard; action=is_shown uses mobile: isKeyboardShown. |
| appium_get_textC | Get text from an element |
| appium_get_element_attributeA | Get the value of an element attribute. Use this to check element state (enabled, selected, checked, focused, displayed, clickable) or read properties (name, value, label, content-desc, resource-id, class). |
| appium_mobile_clipboardA | Read or set the device clipboard as plain text (Android UiAutomator2 / iOS XCUITest). action=get returns current text; action=set requires content. |
| appium_get_active_elementA | Get the currently active/focused element and return its UUID for follow-up interactions. [PRIORITY 1: Use this first when you need to find what element currently has focus] |
| appium_get_page_sourceB | Get the page source (XML) from the current screen |
| appium_orientationA | Get or set the device/screen orientation. Supports action=get and action=set (LANDSCAPE or PORTRAIT). |
| appium_alertA | Handle system alerts with action=accept|dismiss, or read alert text with action=get_text. |
| appium_screenshotA | Take a screenshot and save as PNG. Optionally provide elementUUID to capture only that element. |
| appium_get_window_sizeA | Get the width and height of the device screen in pixels. Useful for calculating coordinates for swipes, taps, and scrolls. |
| appium_screen_recordingA | Start or stop screen recording. action=start begins recording; action=stop stops and saves to MP4. |
| appium_app_lifecycleC | Manage app lifecycle, installation, state, data, and deep links. |
| appium_mobile_permissionsA | Get/update Android app permissions or iOS Simulator privacy services; reset iOS privacy prompts. See action-specific parameters. |
| appium_contextA | Manage Appium contexts with one tool. action=list returns all contexts and current context. action=switch changes to a target context. |
| generate_locatorsA | Generate locators for all interactable elements on the current page. [PRIORITY 3: Use this for debugging/inspection or when you need comprehensive element info with locator suggestions] |
| appium_generate_testsA | Return a workflow to execute the scenario with MCP tools, then generate test code from observed interactions. Prefer appium_find_element; generate_locators is for broad inspection. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Generate Code With Locators | Generate code for the current page with locators which was retrieved from generate_locators tool. The code should be generated in the same priorty order as the locators were generated. Always use the actions API code from the template for the gestures. For iOS the priority order is: 'id', 'accessibility id', '-ios predicate string', '-ios class chain', 'xpath', 'class name', For Android the priority order is: 'id', 'accessibility id', 'xpath', '-android uiautomator', 'class name', which follows the page factory pattern. Dont not strictly create test cases, just generate the code for locators. |
| Appium Page Source Inspector | Interactive inspector for appium_get_page_source results |
| Appium Screenshot Viewer | Interactive viewer for appium_screenshot results |
| Appium Locator Generator | Interactive viewer for generate_locators results |
TDQS
Scored across 31 tools
Each tool targets a distinct resource/action and the descriptions actively cross-reference each other (e.g., appium_gesture defers to appium_drag_and_drop and appium_perform_actions; appium_find_element vs generate_locators vs appium_get_active_element carry priority guidance). Even potentially overlapping gesture and element-lookup tools are clearly separated, so an agent is unlikely to mis-select.
The dominant appium_ + snake_case pattern is consistent across ~27 tools, but select_device, generate_locators, and prepare_ios_simulator break the prefix convention. Notably, generate_locators vs appium_generate_tests and prepare_ios_simulator vs appium_prepare_ios_real_device are internally inconsistent pairs in the same subdomains.
With 31 tools, the surface exceeds the 25+ 'too many' threshold. While Appium's domain is broad, the set is dense and several tools could be consolidated (e.g., the three separate gesture tools, or device_info/orientation/control split across tools), making it heavier than needed for agent usability.
The surface covers the mobile automation lifecycle well: device selection, session management, element finding/interaction, gestures, app lifecycle, contexts, and device services (permissions, geolocation, clipboard, files, recording). Minor gaps exist — no element clear-text operation, no element location/size retrieval, and no explicit wait-for-element helper — but agents can work around these.