広告掲載
MCP.so
ログイン

Mobile Device MCP Server

@saranshbamania

リポジトリ

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

saranshbamania

投稿者

saranshbamania

Mobile Device MCP Server について

MCP server that gives AI coding assistants the ability to see and interact with mobile devices. 49 tools for Android/iOS — AI-powered visual analysis (Claude + Gemini), smart tap/type by description, Flutter widget tree inspection, video recording, and test script generation. 4-t

#mcp#mobile#android#ios#flutter#ai#testing#automation#screenshot#adb#claude#gemini#device-control#visual-analysis

Mobile Device MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

Mobile Device MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Mobile Device Mcp?

Mobile Device Mcp gives AI coding assistants (Claude Code, Cursor, Windsurf) the ability to see and interact with mobile devices. It provides 49 MCP tools across seven categories including Device Control, AI Vision, Flutter, iOS Simulator, Video Recording, Test Generation, and App Management. It is built for developers who need to automate mobile device interactions from their coding environment.

How to use Mobile Device Mcp?

Run npx mobile-device-mcp with zero setup. It automatically discovers ADB, detects connected Android devices, and installs the companion app. For iOS simulators and Flutter apps, additional capabilities are activated when a Dart VM Service is detected. No configuration files are needed to start.

Key features of Mobile Device Mcp

  • 49 MCP tools across 7 categories for device interaction
  • AI Vision tools: smart tap by description, screen analysis, OCR, form filling
  • Flutter widget tree inspection and hot reload/restart via Dart VM Service
  • iOS Simulator control (boot, screenshot, shutdown) via xcrun simctl
  • Test generation: record tool calls and export as TypeScript/Python/JSON scripts
  • Compresses screenshots 89% (251KB to 28KB) with no AI quality loss

Use cases of Mobile Device Mcp

  • Automate mobile app UI testing with screenshot comparisons and element search
  • Inspect and modify Flutter widget trees directly from an AI coding assistant
  • Record a session of device interactions and export it as a reusable test script
  • Perform visual regression testing with diff analysis and OCR
  • Manage apps (install, uninstall, launch, stop) across multiple Android devices

よくある質問

1

Which AI coding assistants are supported?

Claude Code, Cursor, and Windsurf are explicitly supported.

2

What is included in the free tier vs Pro?

Free tier gives 14 tools for device control and basic interaction. Pro unlocks all 49 tools including AI Vision, Flutter, iOS, video recording, and test generation.

3

How does Mobile Device Mcp achieve its performance?

It uses a 4-tier element search that resolves taps in under 1ms locally. The companion Android app retrieves the UI tree 23x faster than UIAutomator (105ms vs 2448ms). Screenshots are compressed 89% with zero AI quality loss.

4

What setup is required for Android devices?

None. Running `npx mobile-device-mcp` auto-discovers ADB, auto-detects connected devices, and auto-installs the companion app.

5

Does it support both Android and iOS?

Yes. Android uses ADB and the companion app; iOS Simulator is controlled via `xcrun simctl`. Flutter support works through the Dart VM Service on either platform.

コメント

「AI とエージェント」の他のコンテンツ

BlazingCDN MCP - Content Delivery for Video, Software & Static Files

BlazingCDN

Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

1

Magic Hour

Magic Hour MCP lets AI agents create and edit images, videos, and audio using Magic Hour’s hosted generation tools.

q-ring

I4cTime

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.

3

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

48

TruVerifAI Panel-review

TruVerifAI

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

1
広告掲載