agent-device
Agent-native CLI for AI mobile testing and app automation across iOS, Android, tvOS, Android TV, macOS, and Linux.
Testing & QAnpx -y agent-device{
"mcpServers": {
"agent-device": {
"command": "npx",
"args": [
"-y",
"agent-device"
]
}
}
}agent-device is a community MCP server that connects AI assistants like Claude to agent-native cli for ai mobile testing and app automation across ios, android, tvos, android tv, macos, and linux. It runs locally on your machine, keeping your data private and giving you full control over the connection. Adding it to your setup expands what Claude can do without any extra coding.
About agent-device
Overview
Agent-native CLI for AI mobile testing and app automation across iOS, Android, tvOS, Android TV, macOS, and Linux.
Links
Topics
agent, device, cli, automation, adb, simctl, devicectl, ios, android, tvos, macos, react-native, observability, diagnostics, network, profiling, performance, mcp, model-context-protocol, mcp-server, ai-agent, mobile-automation, ios-simulator, android-emulator, xcuitest, e2e-testing, cursor, claude-code, expo, mobile-testing, qa-automation, ai-testing, ios-automation, android-automation, simulator, emulator, appium, maestro, detox
Who Should Use agent-device?
- 1Extend Claude and other AI assistants with new capabilities
- 2Automate tasks that previously required manual steps
- 3Connect your existing tools to an AI workflow
- 4Reduce repetitive work by letting AI interact with your services
How to Install agent-device
Before you start
You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.
- 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
- 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
- 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.
The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.