agent-device

callstack/agent-device
★ 4,114 stars TypeScript AI/LLM Updated 3mo ago ✓ Clean
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
View on GitHub → 🛡️ Security & TRiSM Audit →

⚡ What This Server Does & Key Capabilities

The agent-device Model Context Protocol (MCP) server provides seamless integration between AI assistants (such as Claude Desktop, Cursor, and Claude Code) and Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux. By connecting this server, your AI agent gains specialized capabilities to inspect, query, and automate tasks within the AI/LLM domain.

Core Agent Capabilities

💡 Example Prompts to Ask Your AI Agent

Once installed in Claude Desktop or Cursor, try asking your assistant:

"Route this complex analysis task to the connected model and return a structured JSON report."
"Compare the reasoning outputs between two connected models and highlight any discrepancies."

Compatible AI Clients

🟣 Claude Desktop ⚡ Cursor IDE 💻 Claude Code CLI 🌊 Windsurf 🤖 Gemini CLI

Quick Install

Copy the config for your editor. Verify environment variables or setup notes in the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agent-device": {
      "command": "npx",
      "args": [
        "-y",
        "callstack/agent-device"
      ]
    }
  }
}
⚡
Building Production MCP Agents? PRO TOOLKITS
Get the Complete 31,400+ MCP Ecosystem Dataset ($29) or the FastMCP + TypeScript Starter Kit ($39) with turnkey Docker & Cloudflare deployment.

README Documentation

<a href="https://www.callstack.com/open-source?utm_campaign=generic&utm_source=github&utm_medium=referral&utm_content=agent-device" align="center"> <picture> <img alt="agent-device: mobile app automation and verification for AI coding agents" src="website/docs/public/agent-device-banner.jpg"> </picture>

View Full Documentation & Updates on GitHub ↗

Topics

adbagentic-aiagentsai-agentsandroid-emulatorautomatione2e-testingexpoflutterios-simulatormcpmobilemobile-testingperformance-optimizationreact-native
📊
Building AI Agents or Backtesting Quant Models?
Get the Polymarket Historical Dataset — 23.0M+ 15-minute price & orderbook snapshots across 18,400+ prediction markets. Clean CSV & SQLite download for backtesting & agent training.
Buy Dataset ($19) → View Sample →