# Agent Device

> Use this tool when you need to automate testing and control of native applications across multiple platforms, including mobile, TV, and desktop devices. It solves problems related to cross-platform compatibility and debugging by providing unified workflows and debugging tools. The Agent Device takes accessibility tree snapshots and semantic commands as input and outputs logs, network dumps, and screen recordings, making it ideal for use cases that require automated testing and quality assurance.

Canonical page: https://skillsregistry.net/skills/agent-device  
JSON: https://api.skillsregistry.net/v1/skills/agent-device

## Description

Agent Device enables AI agents to control and test native mobile, TV, and desktop applications through accessibility tree snapshots and semantic commands. Built by Callstack, it supports iOS, Android, macOS, and Linux with unified workflows, session recording, and debugging tools including logs, network dumps, and screen recordings. The MCP server provides discovery and routing tools while device automation runs through the CLI.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agent-device)
- **Repository:** <https://github.com/callstack/agent-device>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "agent-device"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agent-device` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agent-device/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt