mobile-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MOBILEMCP_AUTH | No | Require a Bearer token on the SSE server — every request must then send Authorization: Bearer <token>. | |
| MOBILEMCP_LEGACY_ROBOT | No | Use the legacy platform-specific robots for Android devices and physical iOS devices. iOS simulators continue to use mobilecli. | |
| MOBILEMCP_ALLOW_UNSAFE_URLS | No | Allow mobile_open_url to open non-standard URL schemes (blocked by default). | |
| MOBILEMCP_DISABLE_TELEMETRY | No | Disable anonymous usage telemetry. |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mobile_list_available_devicesA | List all available devices. This includes both physical mobile devices and mobile simulators and emulators. It returns both Android and iOS devices. |
| mobile_list_appsA | List all the installed apps on the device |
| mobile_launch_appB | Launch an app on mobile device. Use this to open a specific app. You can find the package name of the app by calling list_apps_on_device. |
| mobile_terminate_appB | Stop and terminate an app on mobile device |
| mobile_install_appB | Install an app on mobile device |
| mobile_uninstall_appB | Uninstall an app from mobile device |
| mobile_get_screen_sizeA | Get the screen size of the mobile device in pixels |
| mobile_click_on_screen_at_coordinatesA | Click on the screen at given x,y coordinates. If clicking on an element, use the list_elements_on_screen tool to find the coordinates. |
| mobile_double_tap_on_screenA | Double-tap on the screen at given x,y coordinates. |
| mobile_long_press_on_screen_at_coordinatesA | Long press on the screen at given x,y coordinates. If long pressing on an element, use the list_elements_on_screen tool to find the coordinates. |
| mobile_list_elements_on_screenA | List elements on screen and their coordinates, with display text or accessibility label. Do not cache this result. |
| mobile_press_buttonC | Press a button on device |
| mobile_open_urlA | Open a URL in browser on device |
| mobile_swipe_on_screenC | Swipe on the screen |
| mobile_type_keysA | Type text into the focused element |
| mobile_save_screenshotA | Save a screenshot of the mobile device to a file |
| mobile_take_screenshotA | Take a screenshot of the mobile device. Use this to understand what's on screen, if you need to press an element that is available through view hierarchy then you must list elements on screen instead. Do not cache this result. |
| mobile_set_orientationA | Change the screen orientation of the device |
| mobile_get_orientationA | Get the current screen orientation of the device |
| mobile_start_screen_recordingA | Start recording the screen of a mobile device. The recording runs in the background until stopped with mobile_stop_screen_recording. Returns the path where the recording will be saved. |
| mobile_stop_screen_recordingA | Stop an active screen recording on a mobile device. Returns the file path, size, and approximate duration of the recording. |
| mobile_list_crashesA | List crash reports available on the device |
| mobile_get_crashA | Get the full content of a crash report by its ID. Use mobile_list_crashes to find available crash IDs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 23 tools
Most tools are distinct, but 'mobile_take_screenshot' and 'mobile_save_screenshot' overlap significantly in purpose, which could confuse an agent. Additionally, gesture tools like 'mobile_click_on_screen_at_coordinates' and 'mobile_double_tap_on_screen' have similar naming, though their actions are clearly different.
The 'mobile_' prefix and verb_noun pattern are mostly consistent, but there are deviations such as 'mobile_click_on_screen_at_coordinates' versus 'mobile_double_tap_on_screen' which omits the 'at_coordinates' suffix. A few tool names are longer and less uniform, but overall the pattern is recognizable.
With 23 tools, the server is above the typical well-scoped range of 3-15, but the breadth of mobile automation features (app management, gestures, orientation, screenshots, etc.) justifies most tools. The count feels slightly heavy but not redundant.
The tool set covers core mobile device operations well: app lifecycle, screen interaction, orientation, screenshots, and crash retrieval. Minor gaps exist, such as no explicit device info tool (e.g., model, OS version) and no update for existing apps, but these are not critical for most workflows.