AVD MCP Server
Automates Android Virtual Device operations by enabling users to start emulators, execute development commands, and capture screenshots. It facilitates Android testing workflows by returning command outputs and visual feedback directly to AI assistants.
README
AVD MCP Server
A Model Context Protocol (MCP) server for Android Virtual Device automation. This tool allows you to start an Android emulator, execute commands, and capture screenshots automatically.
Features
- Automatically starts Android Virtual Device (AVD) if not running
- Executes commands (pnpm, gradle, npm, etc.)
- Captures screenshots from the emulator
- Returns command output and screenshot in base64 format
Prerequisites
- Android SDK with
adbandemulatorin PATH - Node.js 18 or higher
- An Android Virtual Device configured in Android Studio
Installation
Quick Start (Recommended)
No installation needed! Just add to your MCP client config (e.g., Claude Desktop):
json { "mcpServers": { "avd-mcp": { "command": "npx", "args": ["avd-mcp"] } } }
That's it! The package will be automatically downloaded and executed when needed.
Local Development
``bash
Clone the repository
git clone https://github.com/yourusername/avd-mcp.git cd avd-mcp
Install dependencies
pnpm install
Build the project
pnpm build
Test locally
node dist/index.js ``
Usage
Available Tools
avd_run_and_screenshot
Starts an AVD (if not running), executes a command, waits, and captures a screenshot.
Parameters:
avdName(optional): Name of the AVD to start. If omitted and no device is running, will throw an error.command(required): Command to execute (e.g.,pnpm android,gradle assembleDebug)waitMsAfterRun(optional): Milliseconds to wait after command execution before taking screenshot. Default: 2000ms
Returns:
- Command output (stdout/stderr)
- Screenshot in base64 format (PNG)
Example:
typescript { "avdName": "Pixel_5_API_31", "command": "pnpm android", "waitMsAfterRun": 5000 }
How It Works
- Device Check: Checks if an Android device/emulator is already running using
adb devices - Start Emulator: If no device is running and
avdNameis provided, starts the emulator - Execute Command: Runs the specified command using PowerShell
- Wait: Waits for the specified duration to allow UI updates
- Screenshot: Captures a screenshot using
adb screencap - Return: Returns both command output and screenshot
Troubleshooting
AVD not starting
- Verify AVD name matches one configured in Android Studio:
emulator -list-avds - Check that
emulatoris in your system PATH - Ensure virtualization is enabled in BIOS (Intel VT-x or AMD-V)
ADB not found
- Install Android SDK Platform-Tools
- Add Android SDK platform-tools to PATH:
C:\Users\YourUser\AppData\Local\Android\Sdk\platform-tools
Screenshot timeout
- Increase
waitMsAfterRunparameter - Check if device is fully booted:
adb shell getprop sys.boot_completed(should return1)
Publishing to npm
To publish this package to npm:
``bash
Login to npm
npm login
Update version in package.json
npm version patch # or minor, or major
Publish
npm publish ``
After publishing, users can use it directly with npx avd-mcp without cloning!
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see LICENSE file for details.
Author
Created for automating Android development workflows with AI assistants.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。