Agent Droid Bridge

Returns all visible text on the current Android screen, sorted top-to-bottom. Use this when you need to read what is on screen. Does not include coordinates or element info — for tapping or interacting, use `get_screen_elements`.

Returns the current Android screen as an XML UI hierarchy. Use this when you need to locate element coordinates, read text, or find resource IDs to interact with. Do not call this after every action — only call it when you actually need to read screen content. To check if the screen changed after an action, use snapshot_ui before the action and detect_ui_change after.

A tap gesture at the given pixel coordinates on the Android screen.

A swipe gesture on the Android screen from (x1,y1) to (x2,y2) over the given duration.

Text input into the currently focused Android input field. Spaces are encoded automatically.

A key event sent to the Android device using the given keycode integer.

A PNG screenshot of the current Android device screen with width, height, and base64-encoded image data.

All Android devices currently visible to ADB, with their serial numbers, connection state, and model names.

An Android app launched by its component name (package/activity).

The output of an ADB command. Parsed safely via shlex and never passed to a system shell.

Takes a lightweight snapshot of the current UI state and returns a short token. Use this before performing an action (tap, swipe, launch, key press) when you only need to confirm the screen changed afterward — not read its content. Pass the returned token to detect_ui_change as baseline_token. This avoids loading the full XML hierarchy into context unnecessarily. Do not use this when you need to read or interact with screen elements — use get_ui_hierarchy for that.

Polls the UI hierarchy after an action and returns when the screen content changes or the timeout is reached. Returns changed status and elapsed time. By default, omits the XML hierarchy for efficiency — set return_hierarchy=True to receive the full hierarchy. For efficient change detection: call snapshot_ui before the action, perform the action, then call detect_ui_change with baseline_token. Only use without baseline_token when you need to wait for a slow transition (loading screens, animations). Do not use to read the current screen state — use get_ui_hierarchy for that.

Structured list of UI elements currently visible on the Android screen. Returns elements filtered and shaped by the chosen mode. Prefer 'tappable' for navigation and 'interactive' when you need XPath or bounds for ADB commands. Only use 'all' as a last resort — it returns every node and can be large.

Device capabilities and hardware profile for the connected Android device. Use 'identity' to establish what device you are working with before starting a session. Use 'security' when a task requires root permissions or you need to confirm privilege level. Use 'hardware' when you need screen dimensions or memory constraints for layout decisions. Use 'all' only when you need a complete profile and latency is not a concern.

List installed packages on the device. Use search to narrow results before requesting detailed mode — detailed runs a separate dumpsys call per package and is expensive on large lists.

Full static metadata for a single installed app. Request only the sections you need. Use search to filter components or permissions by name.

Install an APK from a host path onto the device. Returns the package name and version if aapt is available, or None for those fields if not. Returns the package manager error string on failure.

Remove an installed app by package name.

Extract the installed APK from the device by package name. Returns the written file path(s) and sizes.

Grant, revoke, check, or list runtime permissions for an app. Use list to see all permissions without specifying one. Use check to verify grant status before acting.

Launch an app by package name without requiring a component name. Resolves the launcher activity automatically using pm resolve-activity. Returns the resolved component, app name, and PID when available. PID is best-effort — it may be None on success if the process had not registered by the time of the check. If resolution fails, the error message will suggest using get_app_info with sections=['components'] followed by launch_app with the explicit component.

Control app runtime state. Clear_data is irreversible — it permanently removes all user data for the app. Clear_cache requires root and reports requires_root=true when unavailable.

Fire an intent at a component. Requires intent_type: 'activity', 'broadcast', or 'service'. Broadcasts can produce verbose output — use filter to extract relevant lines. Returns success, exit code, filtered or full output lines, and error if any. For advanced intent flags not covered here, use execute_adb_command directly.