Skip to main content
Glama
pedro-rivas

Android Puppeteer

by pedro-rivas
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
list_emulatorsA

List all available Android emulators and devices with their name, ID, status, and dimensions

take_screenshotB

Take a screenshot for the specified device/emulator. If no device_id is provided, uses the default device. Set annotate_elements=False to take a plain screenshot without UI element annotations.

pressB

Tap on specific coordinates on the Android screen. Use duration for long press (in milliseconds).

long_pressC

Long press on specific coordinates on the Android screen.

get_ui_elements_infoC

Get detailed information about all interactive UI elements on the screen including their coordinates and properties.

get_device_dimensionsC

Get the dimensions of the Android device/emulator screen.

press_backA

Press the hardware back button on the Android device/emulator.

swipeB

Swipe horizontally or vertically on the Android screen.

Args:
    direction: 'left', 'right', 'up', 'down' for directional swipes
    x1, y1, x2, y2: Exact coordinates for custom swipes
    device_id: Optional device ID to target specific device/emulator
    distance: Distance of swipe in pixels (default: 50% of screen dimension)
    duration: Duration of swipe in milliseconds (default: 300ms)
type_textA

Type text into the currently focused input field on the Android device/emulator.

Args:
    text: The text to type into the input field
    device_id: Optional device ID to target specific device/emulator
    clear_first: If True, clears existing text before typing new text
scroll_elementA

Scroll a specific UI element in the given direction for a specified distance.

Args:
    element: Either an integer (element index from annotated screenshot) or string (element name)
    direction: Direction to scroll - 'up', 'down', 'left', 'right'
    distance: Distance to scroll in pixels (default: 200)
    duration: Duration of scroll gesture in milliseconds (default: 300)
    device_id: Optional device ID to target specific device/emulator
record_videoC

Start recording a video using scrcpy. The video will be saved to the videos directory.

stop_videoC

Stop the active video recording for the specified device.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 12 tools

Disambiguation4/5

Most tools have distinct purposes for Android device interaction, but 'press' and 'long_press' overlap in functionality as both handle screen touches with duration parameters, which could cause confusion. Other tools like 'get_device_dimensions' and 'get_ui_elements_info' are clearly differentiated.

Naming Consistency5/5

All tool names follow a consistent snake_case pattern with clear verb_noun structure (e.g., 'take_screenshot', 'type_text', 'scroll_element'). The naming is predictable and readable throughout the set.

Tool Count5/5

With 12 tools, this server is well-scoped for Android automation, covering essential actions like input, navigation, and media capture. Each tool serves a specific role without bloat, fitting typical automation needs.

Completeness4/5

The toolset covers core Android interaction workflows including input, navigation, and media, but lacks tools for advanced tasks like app management (e.g., install/uninstall) or system settings. Minor gaps exist, but agents can perform basic automation effectively.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources