adb-mcp
Related Servers
Alternatives to adb-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityAmaintenanceA comprehensive MCP server that enables AI agents to interact with Android devices through Android Debug Bridge (ADB), offering 198 tools for device control, app management, diagnostics, and more.10034 npm19Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA powerful MCP server that provides comprehensive Android device automation capabilities through ADB, enabling AI agents to interact with Android devices for testing, automation, and device control tasks.1-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that wraps Android ADB functionality into AI assistant tools, enabling device management, shell execution, file operations, app management, media capture, and log analysis via natural language.16 npm2MIT
- FlicenseAqualityDmaintenanceA MCP server that enables AI assistants to control Android devices via ADB, supporting device info, screen control, input simulation, app management, shell execution, file transfer, and UI parsing.20-
- FlicenseAqualityDmaintenanceAn MCP server designed for Android development, enabling AI assistants to directly control Android devices for screenshots, UI analysis, app management, and more.19-
- AlicenseAqualityBmaintenanceMCP server for Android device control via ADB and scrcpy, enabling AI agents to see and interact with Android devices.46154 npmMIT
TDQS
Scored across 90 tools
Many tools have distinct purposes, but several overlapping groups exist (e.g., capture_screen variants, tap vs tap_element, launch_package vs launch_activity, force_stop vs kill_background, logcat_dump vs logcat_filter). With 90 tools, an agent may struggle to select the right one, though descriptions help clarify boundaries.
All tool names use snake_case, providing a consistent surface style. However, there is a mix of verb_noun (list_packages, get_devices) and bare verbs (connect, reboot, tap), and inconsistent verb choices for similar operations (set_prop vs put_setting). These are minor deviations from a uniform pattern.
90 tools is far above the recommended 3-15 range and exceeds the 50+ threshold for extreme mismatch. While ADB is a complex domain, the tool count is excessive and many tools could be consolidated (e.g., screen capture variants, logcat controls), creating a high cognitive load for agents.
The set covers a very broad range of ADB functionality: device management, app lifecycle, file operations, input, logging, screen capture, networking, settings, and UI automation. Minor gaps exist (e.g., setting display size/density, managing users, kernel logs), but agents can work around most tasks.