Skip to main content
Glama

MCP server that gives AI coding assistants (Claude Code, Cursor, Windsurf) the ability to see and interact with mobile devices. 49 tools for screenshots, UI inspection, touch interaction, AI-powered visual analysis, Flutter widget tree inspection, video recording, and test generation.

AI assistants can read your code but can't see your phone. This fixes that.

Why This One?

Feature

mobile-device-mcp

mobile-next/mobile-mcp

appium/appium-mcp

Total tools

49

20

~15

Setup

npx (30 sec)

npx

Requires Appium server

AI visual analysis

12 tools (Claude + Gemini)

None

Vision-based finding

Flutter widget tree

10 tools (Dart VM Service)

None

None

Smart element finding

4-tier (<1ms local search)

Accessibility tree only

XPath/selectors

Companion app (23x faster UI tree)

Yes

No

No

Video recording

Yes

No

No

Test script generation

TS, Python, JSON

No

Java/TestNG only

iOS simulator support

Yes

Yes

Yes

iOS real device

Planned

Yes

Yes

Screenshot compression

89% (251KB->28KB)

None

50-80%

Multi-provider AI

Claude + Gemini

N/A

Single provider

Price

Free + Pro (₹499/mo)

Free

Free

Related MCP server: Flutter Driver MCP

The Problem

Web developers have browser DevTools, Playwright, and Puppeteer -- AI assistants can click around, take screenshots, and verify fixes. Mobile developers? They're stuck manually screenshotting, copying logs, and describing what's on screen. They're human middleware between the AI and the device.

What This Does

Developer: "The login button doesn't work"

Without this tool:                    With this tool:
  1. Manually screenshot              1. AI calls take_screenshot -> sees the screen
  2. Paste into AI chat               2. AI calls smart_tap("login button") -> taps it
  3. AI guesses what's wrong          3. AI calls verify_screen("error message shown") -> sees result
  4. Apply fix, rebuild               4. AI calls visual_diff -> confirms fix worked
  5. Repeat 4-5 times                 5. Done.

Quick Start

Install

npx mobile-device-mcp

No global install needed. Runs directly via npx.

Prerequisites

Setup (One-time, 30 seconds)

  1. Get a Google AI key (free tier available): aistudio.google.com/apikey

  2. Add .mcp.json to your project root:

macOS / Linux:

{
  "mcpServers": {
    "mobile-device": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mobile-device-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key"
      }
    }
  }
}

Windows:

{
  "mcpServers": {
    "mobile-device": {
      "type": "stdio",
      "command": "cmd",
      "args": ["/c", "npx", "-y", "mobile-device-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key"
      }
    }
  }
}

With Pro license key (after purchasing Pro):

{
  "mcpServers": {
    "mobile-device": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mobile-device-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "MOBILE_MCP_LICENSE_KEY": "MDMCP-XXXXX-XXXXX-XXXXX-XXXXX"
      }
    }
  }
}
{
  "mcpServers": {
    "mobile-device": {
      "type": "stdio",
      "command": "cmd",
      "args": ["/c", "npx", "-y", "mobile-device-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "MOBILE_MCP_LICENSE_KEY": "MDMCP-XXXXX-XXXXX-XXXXX-XXXXX"
      }
    }
  }
}
  1. Open your AI coding assistant from that directory. That's it.

The server starts and stops automatically -- you never run it manually. Your AI assistant manages it as a background process via the MCP protocol.

Verify It Works

Claude Code: type /mcp -- you should see mobile-device: Connected

Cursor: check MCP panel in settings

Then just talk to your phone:

You: "Open my app, tap the login button, type test@email.com in the email field"
AI:  [takes screenshot -> sees the screen -> smart_tap("login button") -> smart_type("email field", "test@email.com")]

You: "Find all the bugs on this screen"
AI:  [analyze_screen -> inspects layout, checks for overflow, missing labels, broken states]

You: "Navigate to settings and verify dark mode works"
AI:  [smart_tap("settings") -> take_screenshot -> smart_tap("dark mode toggle") -> visual_diff -> reports result]

No test scripts. No manual screenshots. Just describe what you want in plain English.

Works with Any AI Coding Assistant

Tool

Config file

Docs

Claude Code

.mcp.json in project root

claude.ai/docs

Cursor

.cursor/mcp.json

cursor.com/docs

VS Code + Copilot

MCP settings

code.visualstudio.com

Windsurf

MCP settings

windsurf.com

All use the same JSON config -- just put it in the right file for your editor.

Drop Into Any Project

Copy .mcp.json into any mobile project -- Flutter, React Native, Kotlin, Swift -- and your AI assistant gets device superpowers in that directory. No global install needed.

Free vs Pro

Free (14 tools) -- no license key needed

Tool

What it does

list_devices

List all connected Android devices/emulators

get_device_info

Model, manufacturer, Android version, SDK level

get_screen_size

Screen resolution in pixels

take_screenshot

Capture screenshot (PNG or JPEG, configurable quality & resize)

get_ui_elements

Get the accessibility/UI element tree as structured JSON

tap

Tap at coordinates

double_tap

Double tap at coordinates

long_press

Long press at coordinates

swipe

Swipe between two points

type_text

Type text into the focused field

press_key

Press a key (home, back, enter, volume, etc.)

list_apps

List installed apps

get_current_app

Get the foreground app

get_logs

Get logcat entries with filtering

Pro (35 additional tools) -- ₹499/mo

Get Pro License -- unlock all 49 tools. After payment, you'll receive your license key via email within 1 hour. Add it to your .mcp.json:

{
  "mcpServers": {
    "mobile-device": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mobile-device-mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key",
        "MOBILE_MCP_LICENSE_KEY": "your-license-key"
      }
    }
  }
}

AI Visual Analysis (12 tools)

Use AI vision (Claude or Gemini) to understand what's on screen.

Tool

What it does

analyze_screen

AI describes the screen: app name, screen type, interactive elements, visible text, suggestions

find_element

Find a UI element by description: "the login button", "email input field"

smart_tap

Find an element by description and tap it in one step

smart_type

Find an input field by description, focus it, and type text

suggest_actions

Plan actions to achieve a goal: "log into the app", "add item to cart"

visual_diff

Compare current screen with a previous screenshot -- what changed?

extract_text

Extract all visible text from the screen (AI-powered OCR)

verify_screen

Verify an assertion: "the login was successful", "error message is showing"

wait_for_settle

Wait until the screen stops changing

wait_for_element

Wait for a specific element to appear on screen

handle_popup

Detect and dismiss popups, dialogs, permission prompts

fill_form

Fill multiple form fields in one step

Flutter Widget Tree (10 tools)

Connect to running Flutter apps via Dart VM Service Protocol. Maps every widget to its source code location (file:line).

Tool

What it does

flutter_connect

Discover and connect to a running Flutter app on the device

flutter_disconnect

Disconnect from the Flutter app and clean up resources

flutter_get_widget_tree

Get the full widget tree (summary or detailed)

flutter_get_widget_details

Get detailed properties of a specific widget by ID

flutter_find_widget

Search the widget tree by type, text, or description

flutter_get_source_map

Map every widget to its source code location (file:line:column)

flutter_screenshot_widget

Screenshot a specific widget in isolation

flutter_debug_paint

Toggle debug paint overlay (shows widget boundaries & padding)

flutter_hot_reload

Hot reload Flutter app (preserves state)

flutter_hot_restart

Hot restart Flutter app (resets state)

iOS Simulator (4 tools)

macOS only. Control iOS simulators via xcrun simctl.

Tool

What it does

ios_list_simulators

List available iOS simulators

ios_boot_simulator

Boot a simulator by name or UDID

ios_shutdown_simulator

Shut down a running simulator

ios_screenshot

Take a screenshot of a simulator

Video Recording (2 tools)

Tool

What it does

record_screen

Start recording the device screen

stop_recording

Stop recording and save the video

Test Generation (3 tools)

Tool

What it does

start_test_recording

Start recording your MCP tool calls

stop_test_recording

Stop recording and generate a test script

get_recorded_actions

Get recorded actions as TypeScript, Python, or JSON

App Management (4 tools)

Tool

What it does

launch_app

Launch an app by package name

stop_app

Force stop an app

install_app

Install an APK

uninstall_app

Uninstall an app

Performance

The server is optimized to minimize latency and AI token costs:

  • 4-tier element search: companion app (instant) -> local text match (<1ms) -> cached AI -> fresh AI. smart_tap is 35x faster than naive AI calls (205ms vs 7.6s).

  • Companion app: AccessibilityService-based Android app provides UI tree in 105ms (23x faster than UIAutomator's 2448ms). Auto-installs on first use.

  • Screenshot compression: AI tools auto-compress to JPEG q=60, 400w -- 89% smaller (251KB -> 28KB) with zero AI quality loss.

  • Parallel capture: Screenshot + UI tree fetched simultaneously via Promise.all().

  • TTL caching: 5-second cache avoids redundant ADB calls for rapid-fire tool usage.

Environment Variables

Variable

Description

Default

GOOGLE_API_KEY or GEMINI_API_KEY

Google API key for Gemini vision (recommended)

--

ANTHROPIC_API_KEY

Anthropic API key for Claude vision

--

MOBILE_MCP_LICENSE_KEY

License key to unlock Pro tools

--

MCP_AI_PROVIDER

Force AI provider: "anthropic" or "google"

Auto-detected

MCP_AI_MODEL

Override AI model

gemini-2.5-flash / claude-sonnet-4-20250514

MCP_ADB_PATH

Custom ADB binary path

Auto-discovered

MCP_DEFAULT_DEVICE

Default device serial

Auto-discovered

MCP_SCREENSHOT_FORMAT

"png" or "jpeg"

jpeg

MCP_SCREENSHOT_QUALITY

JPEG quality (1-100)

80

MCP_SCREENSHOT_MAX_WIDTH

Resize screenshots to this max width

720

Architecture

src/
|-- index.ts              # CLI entry point (auto-discovery, env config)
|-- server.ts             # MCP server factory
|-- license.ts            # License validation and tier gating
|-- types.ts              # Shared interfaces
|-- drivers/android/      # ADB driver (DeviceDriver implementation)
|   |-- adb.ts            # Low-level ADB command wrapper
|   |-- companion-client.ts # TCP client for companion app
|   +-- index.ts          # AndroidDriver class (4-strategy UI element retrieval)
|-- drivers/flutter/      # Dart VM Service driver
|   |-- index.ts          # FlutterDriver (discovery, inspection, source mapping, hot reload)
|   +-- vm-service.ts     # JSON-RPC 2.0 WebSocket client (DDS redirect handling)
|-- drivers/ios/          # iOS Simulator driver (macOS only)
|   |-- index.ts          # IOSSimulatorDriver via xcrun simctl
|   +-- simctl.ts         # Low-level simctl command wrapper
|-- tools/                # MCP tool registrations (free + pro gating)
|   |-- device-tools.ts   # Device management
|   |-- screen-tools.ts   # Screenshots & UI inspection
|   |-- interaction-tools.ts # Touch, type, keys
|   |-- app-tools.ts      # App management
|   |-- log-tools.ts      # Logcat
|   |-- ai-tools.ts       # AI-powered tools
|   |-- flutter-tools.ts  # Flutter widget inspection
|   |-- ios-tools.ts      # iOS simulator tools
|   |-- video-tools.ts    # Screen recording
|   +-- recording-tools.ts # Test generation
|-- recording/            # Test script generation
|   |-- recorder.ts       # ActionRecorder (records MCP tool calls)
|   +-- generator.ts      # TestGenerator (TypeScript/Python/JSON output)
|-- ai/                   # AI visual analysis engine
|   |-- client.ts         # Multi-provider client (Anthropic + Google)
|   |-- prompts.ts        # System prompts & UI element summarizer
|   |-- analyzer.ts       # ScreenAnalyzer orchestrator (caching, parallel capture)
|   +-- element-search.ts # Local element search (text/alias matching, no AI needed)
+-- utils/
    |-- discovery.ts      # ADB auto-discovery
    +-- image.ts          # PNG parsing, JPEG compression, bilinear resize

companion-app/            # Android companion app (Kotlin)
                          # AccessibilityService + TCP JSON-RPC for fast UI tree

Roadmap

  • iOS physical device support

  • Multi-device orchestration

  • CI/CD integration

  • Cloud device farm support

Tested On

  • Devices: Pixel 8 (Android 16), Samsung Galaxy series, Android emulators

  • Apps: Telegram, Instagram, Spotify, WhatsApp, YouTube, Chrome, Settings, and Flutter apps

  • AI Providers: Google Gemini 2.5 Flash, Anthropic Claude

  • Platforms: Windows 11, macOS (iOS simulators)

  • Connection: USB and wireless ADB

License

Business Source License 1.1

  • Free for individuals and non-commercial use

  • Commercial use requires a paid license

  • Converts to Apache 2.0 on March 23, 2030

See LICENSE for full terms.

Available Tools

49 tools
analyze_screenAnalyze Screen (AI) [Pro]A

[Pro] Uses AI vision to analyze the current screen of a mobile device. Returns a structured analysis including app name, screen type, interactive elements with coordinates, visible text, and suggested next actions. This is the primary tool for understanding what is currently displayed on the device.

Inputs: device_id (required).

double_tapDouble TapA

Perform a double tap at the given (x, y) screen coordinates. Useful for zooming into maps/images or selecting text.

Inputs: device_id (required), x (required), y (required).

extract_textExtract Text from Screen (AI) [Pro]A

[Pro] Uses AI vision to extract all visible text from the current screen. Returns text in reading order (top to bottom, left to right). Useful for reading content, checking labels, or getting text that isn't in the accessibility tree.

Inputs: device_id (required).

fill_formFill Form [Pro]A

[Pro] Fill multiple form fields in a single operation. Provide a map of field descriptions to values. Each field is found by natural language description, cleared, and filled with the specified value. More efficient than calling smart_type multiple times.

Inputs: device_id (required), fields (required).

find_elementFind Element by Description (AI) [Pro]A

[Pro] Uses AI vision to find a specific UI element by natural language description. Returns the element's coordinates, type, and confidence score. Use this when you need to locate a specific button, field, or other UI element. Example queries: 'the login button', 'email input field', 'the red error message'.

Inputs: device_id (required), query (required).

flutter_connectConnect to Flutter App [Pro]A

[Pro] Discover and connect to a running Flutter app on the device via the Dart VM Service Protocol. The app must be running in debug or profile mode. Returns connection details including the isolate ID and app name. Call this before using other flutter_* tools. Optionally pass vm_service_url from 'flutter run' output if auto-discovery fails.

Inputs: device_id (required), vm_service_url.

flutter_debug_paintToggle Flutter Debug Paint [Pro]A

[Pro] Toggle the debug paint overlay on the Flutter app. Shows widget boundaries, padding, alignment guides, and construction lines. Useful for debugging layout issues.

Inputs: enabled.

flutter_disconnectDisconnect from Flutter App [Pro]A

[Pro] Disconnect from the currently connected Flutter app and clean up resources.

Inputs: no named parameters.

flutter_find_widgetFind Flutter Widget [Pro]B

[Pro] Search the widget tree for widgets matching a query. Searches by widget type name, description, and text content. Example queries: 'ElevatedButton', 'Text', 'AppBar', 'Login'. Returns matching widgets with their source locations.

Inputs: query (required), summary_only.

flutter_get_source_mapGet Flutter Source Map [Pro]A

[Pro] Map every user-created widget to its source code location (file:line:column). This is the key tool for connecting what you see on screen to where it is in code. Returns a list of {widget, file, line, column} entries.

Inputs: no named parameters.

flutter_get_widget_detailsGet Flutter Widget Details [Pro]B

[Pro] Get detailed information about a specific widget by its valueId (obtained from flutter_get_widget_tree). Returns properties, children, render bounds, and source location.

Inputs: value_id (required), subtree_depth.

flutter_get_widget_treeGet Flutter Widget Tree [Pro]A

[Pro] Get the widget tree from the connected Flutter app. By default returns the summary tree (user-created widgets only), which maps directly to your source code. Each widget includes its type, properties, source code location (file:line), and children. Call flutter_connect first.

Inputs: summary_only.

flutter_hot_reloadFlutter Hot Reload [Pro]A

[Pro] Trigger a hot reload on the connected Flutter app. Pushes code changes without losing app state — variables, navigation stack, and scroll positions are preserved. Much faster than a full restart. Call flutter_connect first.

Inputs: no named parameters.

flutter_hot_restartFlutter Hot Restart [Pro]A

[Pro] Trigger a hot restart on the connected Flutter app. Restarts the app from scratch, losing all state, but applies all code changes including static field initializers and global variables. Use when hot reload is insufficient. Call flutter_connect first.

Inputs: no named parameters.

flutter_screenshot_widgetScreenshot Flutter Widget [Pro]B

[Pro] Take a screenshot of a specific Flutter widget by its valueId. Returns the widget rendered in isolation as a PNG image.

Inputs: value_id (required), width, height.

get_current_appGet Current AppA

Get the package name and activity name of the app that is currently in the foreground on the device. Useful for determining what the user is currently looking at.

Inputs: device_id (required).

get_device_infoGet Device InfoA

Get detailed information about a specific Android device, including model, manufacturer, Android version, SDK version, connection status, screen size, and whether it is an emulator.

Inputs: device_id (required).

get_logsGet LogsA

Retrieve recent Android logcat entries from the device. You can filter by minimum log level (V=Verbose, D=Debug, I=Info, W=Warning, E=Error, F=Fatal) and/or by tag name. Returns structured JSON with timestamp, PID, TID, level, tag, and message for each entry.

Inputs: device_id (required), lines, level, filter.

get_recorded_actionsGet Recorded Actions [Pro]A

[Pro] View the actions recorded so far without stopping the recording. Useful for inspecting what has been captured.

Inputs: no named parameters.

get_screen_sizeGet Screen SizeA

Get the screen resolution of a connected Android device. Returns the width and height in pixels.

Inputs: device_id (required).

get_ui_elementsGet UI ElementsA

Retrieve the current UI element tree from the device screen. Each element includes its index, text, content description, class name, resource ID, bounding box with center coordinates (useful for tap targets), and boolean states (clickable, scrollable, focusable, enabled, selected, checked). By default only interactive elements are returned. Set interactive_only to false to get all elements. This is the primary tool for understanding what is on screen and deciding where to tap.

Inputs: device_id (required), interactive_only.

handle_popupHandle Popup / Dismiss Dialog [Pro]B

[Pro] Detects and handles system dialogs and popups (permission requests, update prompts, system alerts). Can automatically dismiss or accept the dialog. Use 'dismiss' to decline/skip, 'accept' to allow/confirm, or 'auto' to handle it automatically.

Inputs: device_id (required), action.

install_appInstall App [Pro]A

[Pro] Install an Android application from an APK file on the host machine. Provide the full path to the .apk file. The APK will be pushed to the device and installed.

Inputs: device_id (required), apk_path (required).

ios_boot_simulatorBoot iOS Simulator [Pro]A

[Pro] Boot an iOS simulator by its UDID. Get the UDID from ios_list_simulators.

Inputs: device_id (required).

ios_list_simulatorsList iOS Simulators [Pro]A

[Pro] List all available iOS simulators with their status (Booted/Shutdown), UDID, name, and iOS version. Works on macOS only.

Inputs: no named parameters.

ios_screenshotiOS Simulator Screenshot [Pro]A

[Pro] Take a screenshot of a running iOS simulator. Returns the image as base64.

Inputs: device_id (required), format.

ios_shutdown_simulatorShutdown iOS Simulator [Pro]A

[Pro] Shutdown a running iOS simulator by its UDID.

Inputs: device_id (required).

launch_appLaunch App [Pro]A

[Pro] Launch an installed application by its package name (e.g. 'com.android.chrome'). The app will be started with its default/main activity. Use list_apps to discover available package names.

Inputs: device_id (required), package_name (required).

list_appsList AppsA

List all installed applications on the device. By default only user-installed (non-system) apps are returned. Set include_system to true to also include system apps. Each entry contains the package name, display name, version, and whether it is a system app.

Inputs: device_id (required), include_system.

list_devicesList DevicesA

List all connected Android devices and emulators. Returns an array of DeviceInfo objects including id, model, manufacturer, Android version, connection status, and whether the device is an emulator.

Inputs: no named parameters.

long_pressLong PressA

Perform a long press (touch and hold) at the given (x, y) screen coordinates. Commonly used to open context menus, start drag operations, or trigger secondary actions.

Inputs: device_id (required), x (required), y (required), duration.

press_keyPress KeyA

Press a hardware or system key on the device. Accepts friendly key names such as 'home', 'back', 'enter', 'volume_up', 'volume_down', 'power', 'tab', 'delete', 'menu', 'search', 'app_switch', 'dpad_up', 'dpad_down', 'dpad_left', 'dpad_right', 'camera', 'escape', 'space', 'media_play_pause', 'media_next', 'media_previous'. You may also pass a raw Android keycode number as a string (e.g. '3' for HOME).

Inputs: device_id (required), key (required).

record_screenRecord Device Screen [Pro]A

[Pro] Start recording the device screen as MP4 video. Android has a 3-minute maximum per recording. Only one recording per device at a time. Call stop_recording to finish and save the video.

Inputs: device_id (required), max_duration, bit_rate, resolution.

smart_tapSmart Tap (AI) [Pro]A

[Pro] Finds a UI element by natural language description and taps it. Combines element finding and tapping into a single action. Example: smart_tap('the Sign In button') will locate the button and tap its center coordinates. Returns whether the tap succeeded and which element was tapped.

Inputs: device_id (required), element_description (required).

smart_typeSmart Type (AI) [Pro]A

[Pro] Finds an input field by natural language description, taps it to focus, and types the specified text. Example: smart_type('email field', 'user@example.com') will find the email input, tap it, and type the email address.

Inputs: device_id (required), field_description (required), text (required).

start_test_recordingStart Test Recording [Pro]A

[Pro] Start recording all MCP tool calls to generate a reproducible test script. All subsequent tool calls will be logged until stop_test_recording is called.

Inputs: test_name.

stop_appStop App [Pro]A

[Pro] Force-stop a running application by its package name. This immediately terminates the app process. Useful for resetting app state or freeing resources.

Inputs: device_id (required), package_name (required).

stop_recordingStop Screen Recording [Pro]A

[Pro] Stop an active screen recording and save the MP4 video. Optionally pull the recording file from the device to the host machine.

Inputs: device_id (required), pull_to_path.

stop_test_recordingStop Test Recording [Pro]A

[Pro] Stop recording and generate a test script from the recorded actions. Supports TypeScript, Python, and JSON output formats.

Inputs: format.

suggest_actionsSuggest Actions for Goal (AI) [Pro]A

[Pro] Uses AI to analyze the current screen and suggest a sequence of actions to achieve a specified goal. Returns step-by-step instructions with exact coordinates for each action. Example goals: 'log into the app', 'navigate to settings', 'add an item to cart'.

Inputs: device_id (required), goal (required).

swipeSwipeA

Perform a swipe gesture from (start_x, start_y) to (end_x, end_y). Use this to scroll through lists, dismiss notifications, navigate between pages, or pull down the notification shade. A shorter duration makes the swipe faster (flick), while a longer duration makes it slower (drag).

Inputs: device_id (required), start_x (required), start_y (required), end_x (required), +2 more.

take_screenshotTake ScreenshotA

Capture a screenshot of the device screen. Returns the image with metadata (width, height, file size). Supports PNG (lossless, larger) and JPEG (compressed, smaller). Use format='jpeg' with quality and max_width to reduce image size for AI analysis.

Inputs: device_id (required), format, quality, max_width.

tapTapA

Perform a single tap at the given (x, y) screen coordinates. Use get_ui_elements first to find the centerX/centerY of the element you want to tap.

Inputs: device_id (required), x (required), y (required).

type_textType TextA

Type text into the currently focused input field on the device. Make sure an input field is focused first (tap on it). Special characters and Unicode are supported.

Inputs: device_id (required), text (required).

uninstall_appUninstall App [Pro]A

[Pro] Uninstall an application from the device by its package name. This removes the app and all its data. System apps cannot be uninstalled without root access.

Inputs: device_id (required), package_name (required).

verify_screenVerify Screen State (AI) [Pro]B

[Pro] Uses AI to verify whether a specific assertion about the current screen is true. Returns a boolean result with confidence score and evidence. Example assertions: 'the login was successful', 'an error message is displayed', 'the cart has 3 items'.

Inputs: device_id (required), assertion (required).

visual_diffVisual Diff (AI) [Pro]A

[Pro] Compares the current screen with a previous screenshot to identify what changed. Provide a base64 PNG screenshot as the 'before' image — the tool captures the current screen as the 'after' image. Returns a list of changes with descriptions and regions. Useful for verifying that an action had the expected effect.

Inputs: device_id (required), before_screenshot (required).

wait_for_elementWait for Element to Appear [Pro]A

[Pro] Waits for a specific UI element to appear on screen by polling the UI tree. More reliable and faster than wait_for_settle — returns as soon as the target element is found. Use after navigation to wait for a specific button, text, or field to appear. Example: wait_for_element('Find Routes') after selecting a station.

Inputs: device_id (required), query (required), timeout, poll_interval.

wait_for_settleWait for Screen to Settle [Pro]A

[Pro] Waits for the screen to stop changing after a navigation or action. Polls the UI tree until two consecutive snapshots are identical, indicating animations and loading have completed. Use this after tapping navigation buttons or triggering screen transitions to ensure the new screen is ready for interaction.

Inputs: device_id (required), timeout, poll_interval.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 49 tools

    Disambiguation3/5

    There is some overlap between basic touch tools (tap, double_tap, long_press) and 'smart' variants (smart_tap, smart_type) which use AI to find elements. Also, screenshot tools (take_screenshot, ios_screenshot, flutter_screenshot_widget) could confuse an agent, though their scopes differ slightly (device, iOS simulator, Flutter widget).

    Naming Consistency4/5

    Most tools follow a consistent verb_noun pattern (e.g., get_device_info, launch_app, stop_recording). Some deviations exist like press_key instead of press_keyboard_key, and ios_boot_simulator vs. ios_list_simulators (verb order swapped). But overall the pattern is clear and predictable.

    Tool Count2/5

    The server has 49 tools, which is excessive for a mobile device interaction server. While the domain is broad (Android, iOS, Flutter debugging, screen recording, testing), many tools could be consolidated or are too niche (e.g., separate flutter_* tools). This likely overwhelms agents.

    Completeness4/5

    The tool surface covers most major device interactions: element discovery, tapping, typing, scrolling, apps management, screen recording, logging, iOS simulator control, Flutter debugging, and testing. Minor gaps include lack of drag-and-drop and no direct ADB command execution, but overall it's fairly complete for mobile automation.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that lets AI agents control iOS and Android devices (tap, scroll, type, take screenshots, read UI trees, and run code). Works with multiple devices at the same time.
      91 npm
      53
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      An MCP server that lets AI agents see, tap, type, scroll, and assert inside live Flutter apps — no pre-written tests required.
      28
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      An MCP server that lets AI agents drive real mobile-app automation on connected devices, enabling natural-language test tasks, test case generation, and app/build management for Android and iOS.
      -
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables MCP-compatible AI assistants to see and control Android devices through screenshots, taps, swipes, typing, app management, UI inspection, file transfer, shell commands, and audio/video streaming. It connects over ADB with optional low-latency acceleration for faster input and near-instant screenshots.
      468 npm
      MIT