# ThumbAgent

> ThumbAgent — liushiyi1027-thumbagent. Use this tool when you need to control and monitor Android devices remotely, enabling device diagnostics, app management, and performance monitoring while ensuring safety and security through policy constraints and explicit confirmations. It solves problems related to mobile device management, automation, and testing, providing a local-first interface for AI agents to interact with devices. Ideal for use cases requiring secure, fine-grained control over Android devices, such as automated testing, device diagnostics, and remote monitoring.

Canonical page: https://skillsregistry.net/skills/liushiyi1027-thumbagent  
JSON: https://api.skillsregistry.net/v1/skills/liushiyi1027-thumbagent

## Description

Local-first MCP server that enables AI agents to safely control and observe Android mobile devices, supporting device diagnostics, app lifecycle management, async task execution, and performance monitoring through a policy-constrained interface with explicit confirmations.

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gpwmcx0c4e)
- **Repository:** <https://github.com/LiuShiYi1027/ThumbAgent>

## 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": "liushiyi1027-thumbagent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/liushiyi1027-thumbagent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/liushiyi1027-thumbagent/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
