tap_screen
Sends a tap gesture at pixel coordinates
How to use it
tap_screen is exposed by the Agent Droid Bridge MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the tap_screen tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Agent Droid Bridge
uvx agent-droid-bridgeOther tools in Agent Droid Bridge (22)
Returns structured device information — identity, security posture, and hardware specs — in a single call; supports identity, security, hardware, and all modes
Polls for a UI change after an action; accepts a snapshot token as baseline; returns hierarchy only when requested
Runs an arbitrary ADB or ADB shell command
Returns full static metadata for a single installed app
Parses the UI hierarchy and returns structured elements with coordinates and interaction properties; supports tappable, interactive, input, and all modes
Returns all visible text on screen sorted top-to-bottom, as plain text
Returns the current screen as an XML UI hierarchy
Fires an intent at a component via am start, am broadcast, or am startservice
Installs an APK from a host path onto the device
Launches an app by its package/activity component name
Launches an app by package name, auto-resolving the launcher activity
Lists all Android devices currently visible to ADB with their serial, state, and model
Lists installed packages with optional filtering, search, and detail levels
Controls app runtime state — stop, clear data, clear cache, enable, disable
Grants, revokes, checks, or lists runtime permissions for an app
Sends an Android keycode event (Back, Home, Enter, etc.)
Extracts the installed APK from the device to the host
Takes a lightweight UI snapshot and returns a token for use with detectuichange
Sends a swipe gesture between two points over a given duration
Captures the screen as a base64-encoded PNG
Types text into the focused input field
Removes an installed app by package name