mobile-device-mcp
Related Servers
Alternatives to mobile-device-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceAn MCP server that lets AI agents see, tap, type, scroll, and assert inside live Flutter apps — no pre-written tests required.285 npmMIT
- AlicenseNot gradedqualityBmaintenanceAn 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.66 npm52MIT
- FlicenseNot gradedqualityCmaintenanceAn 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.-
- AlicenseNot gradedqualityAmaintenanceGives MCP-compatible AI assistants vision and control over Android devices — capturing screenshots, tapping, swiping, typing, launching apps, inspecting UI elements, streaming audio/video, transferring files, and running shell commands over ADB, with a fast binary control protocol for near-instant input and screenshots.151 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables 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.151 npmMIT
- AlicenseBqualityBmaintenanceGive any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.66132 PyPI402MIT
TDQS
Scored across 49 tools
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).
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.
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.
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.