A
licenseB
qualityA
maintenanceA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
83
1,648 npm
6,470
MIT
adb-mcp
by iksnerd
Related Servers
Alternatives to adb-mcp
- AlicenseAqualityNot gradedmaintenanceEnables browser automation through Playwright using accessibility tree snapshots instead of screenshots. Supports web scraping, form interactions, testing, and connecting to existing browser sessions with logged-in accounts.239,525 npm5-
Related Servers
- AlicenseAqualityCmaintenanceEnables coding agents to build, drive, and debug Android apps on a real device, with screenshots, UI dumps, local vision model analysis, and lock-safe Gradle builds.21MIT
- AlicenseAqualityDmaintenanceEnables an agent to inspect and interact with Android emulators or physical devices via ADB, capturing UI snapshots, tapping nodes, typing text, and reading app logs.10MIT
- AlicenseAqualityCmaintenanceEnables AI agents to build, deploy, drive, and debug Android apps — managing Gradle builds, emulators, adb deployment, logcat capture, and full UI automation.5356 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to automate Android and iOS devices, including emulators and physical devices, by capturing screenshots, reading UI accessibility trees, performing touch and text input, and managing app lifecycle and logs.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants and IDEs to drive real Android devices and emulators for cross-app UI automation, testing, and diagnostics, including collecting Logcat output and screenshots.Apache 2.0
- AlicenseAqualityCmaintenanceEnables an agent to drive an Android phone attached via USB by reading the screen, deciding next steps, executing actions, and verifying results, all through adb.191MIT
TDQS
A3.7/5.0
Scored across 79 tools
Disambiguation4/5
Tools are largely distinct and well-differentiated, with descriptions that actively contrast near-neighbors like swipe vs drag, tap vs tap_on_text, and logcat vs start_logcat_capture. A few pairs still require careful reading—app_state vs get_app_details and the several launch_* variants—so selection is not completely automatic.
Naming Consistency4/5
The set overwhelmingly uses snake_case with familiar command verbs like list_, set_, get_, start_, stop_, and run_, making categories predictable. Deviations such as doctor, wait, cellular, screenshot, adb_reverse, and object-first names like finger_remove and session_clear_defaults break the strict verb_noun pattern without making the names unreadable.
Tool Count2/5
79 tools is far above the typical 3-15 well-scoped range and even exceeds the 'too many' threshold of 25+. While the Android testing domain is broad, this server mixes device control, Gradle/build, RN/Expo, telephony, sensors, and UI automation into one flat namespace; many narrow one-off emulator tools could be grouped or split out.
Completeness4/5
The surface is remarkably thorough for Android development and testing: scaffolding, building, unit/instrumented tests, coverage, install/launch, UI interaction, device/emulator state, logs, file transfer, and RN/Expo workflows are all covered. Minor gaps exist—no direct AVD create/delete tool and no deterministic fingerprint-enrollment helper—but agents can work around both with the existing UI and device tools.
Maintenance
ActivitySlowing
ResponsivenessResponsive