by callstackincubator · MCP Server · ★ 2.2k
agent-device Device automation CLI for AI agents. Mobile, TV, and desktop apps. lets coding agents run real apps, inspect UI state, interact with visible elements, and collect debugging evidence through one CLI. It is built around token-efficient accessibility snapshots, not pixel-first screenshots. Agents read compact UI trees, locate elements through refs like , perform touch and text actions, and capture screenshots, video, logs, network, CPU/memory/perf, crash-related logs, and React profiles only when evidence is needed. Agents can ingest the current docs from llms-full.txt.
| Stars | 2,221 |
| Forks | 124 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 52.638/100 |
| Open Issues | 25 |
| Last Updated | 2026-05-22 |
| Created | 2026-01-30 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~2451k |
These tools work well together with agent-device for enhanced workflows:
Explore other popular mcp server tools:
agent-device is CLI to control iOS and Android devices for AI agents. It is categorized as a MCP Server with 2.2k GitHub stars.
agent-device is primarily written in TypeScript. It covers topics such as adb, agentic-ai, agents.
You can find installation instructions and usage details in the agent-device GitHub repository at github.com/callstackincubator/agent-device. The project has 2.2k stars and 124 forks, indicating an active community.
agent-device is released under the MIT license, making it free to use and modify according to the license terms.