"How to evaluate an app in an Android emulator" matching MCP servers:

Enables AI agents to control the Android Emulator through adb, including booting AVDs, installing and managing apps, interacting with the UI, taking screenshots, reading logs, and more.

Enables AI assistants to interact with Android devices and emulators via ADB, providing tools for screenshots, UI inspection, touch and text input, app management, and device control.

An MCP server for managing local Android Virtual Devices (AVDs) and their lifecycles using Android SDK tools. It enables users to create, start, and stop emulators, while providing control over virtual sensors like the accelerometer and gyroscope.

Enables coding agents to open the same web page across persistent mobile, tablet, and desktop viewports, interact with it, capture screenshots, inspect the accessible DOM, and run responsive layout audits without losing state between calls.

Enables any MCP assistant to see and operate an Android phone or emulator over plain adb, reading the accessibility tree to tap elements by name and also supporting screenshots, typing, swiping, app launching and installation, and logcat — with nothing installed on the device and no root required.

Enables AI assistants and automation agents to interact with Cisco CUCM Emulator instances through dynamically generated tools for telephony operations, call simulation, routing policies, CDR buffers, and optional offline mock state.

Enables control of Android emulators (MumuEmulator or ADB-connected devices) through natural language, supporting app management, screen interactions (tap/swipe), screenshots, and device information retrieval.

A local, stdio-only Model Context Protocol server that lets coding agents inspect, control, and test Apple iOS Simulators and Google Android Emulators. It exposes 29 typed tools for device lifecycle, app management, UI automation, screenshots, logs, permissions, location, and platform-specific test conditions.

MCP server for Android dev workflows that exposes Gradle, Manifest, and ProGuard context to Claude, with a library of skills for tasks like AGP upgrade and R8 audit.

An MCP server that automatically translates Android app string resources to multiple languages by detecting changes in default strings.xml files using Git diff. It supports batch translation, preserves formatting placeholders, and works with multiple Android modules.

Enables an AI client to control an Android emulator or USB device over ADB by selecting a device, inspecting the UI hierarchy, and performing taps, swipes, text entry, key presses, and app launches. It relies only on Android platform-tools and exposes a compatible tool surface for phone automation.

An MCP server that gives AI agents full control of Android devices and emulators through plain ADB — no companion APK, no extra daemon, no telemetry.

Enables AI agents to control Android devices via ADB, supporting gestures, input, screenshots, UI analysis, and app management.

Exposes Firebase emulator data (Firestore, Auth, Realtime Database, and logs) to AI coding assistants for local development inspection.

Android MCP — 76 ADB-based tools for device, apps, UI, logcat, emulator, files, system, and debug. Includes 7 workflow Prompts (crash investigation, ANR, battery drain).

Provides powerful inspection and interaction tools for connected android devices or emulators.

Enables interaction with Android devices and emulators through ADB, allowing control actions like tapping, text input, screenshots, UI inspection, and app launching through natural language.

Turn any Android phone into an autonomous ARM64 Linux micro-server and AI development appliance with native MCP support.

An MCP server that gives coding agents hands and eyes on an Android device, providing 19 tools for building, testing, installing, UI inspection, input, logs, and toolchain diagnosis. It returns concise, structured results to make the build-debug loop efficient.

Enables Codex to inspect, test, and control Android emulators through adb with strict typed tools, returning screenshots as native MCP images and keeping physical devices and Gradle execution behind explicit opt-in policies.