agent-device MCP Server
callstack/agent-device
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.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
callstack/agent-device is a TypeScript MCP server licensed under MIT. 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. Topics: agentic-ai, agents, automation, mobile, testing, adb, android-emulator, e2e-testing, expo, ios-simulator, mcp, react-native, xcuitest, ai-agents, flutter, mobile-testing, performance-optimization.
Ranked #43 out of 24850 indexed tools.
In the top 1% of all indexed tools.
Has 4,758 GitHub stars.
Used by 30 other projects.
Has 56 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
4,758 stars → well-known project
Last commit today → actively maintained
743/843 issues closed → responsive maintainer
56 contributors → active community
30 dependents → few downstream users
129,084 weekly installs → widely installed
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
<a href="https://www.callstack.com/open-source?utm_campaign=generic&utm_source=github&utm_medium=referral&utm_content=agent-device" align="center">
<picture>
</picture>
</a>
---
# agent-device
**Mobile app automation and verification for AI coding agents.** Give coding agents a live app feedback loop through a CLI, built-in MCP server, or typed Node.js API.
Let your coding agent verify its changes in the running app. `agent-device` lets agents inspect, control, debug, and verify apps on iOS, Android, and HarmonyOS (simulators, emulators, and physical devices), plus tvOS, Android TV, Amazon Vega OS TV (Vega Virtual Device), web, macOS, and Linux. Agents read token-efficient accessibility snapshots instead of reasoning over screenshots alone, act through refs and selectors, and save evidence for review. It also coordinates device access across parallel agent worktrees and connects to remote device clouds.
Works with Claude Code, Codex, Cursor, Windsurf, Cline, Goose, and an Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.