# BoxLite

> Use this tool when you need to interact with desktop applications in a safe and isolated environment, allowing AI agents to perform tasks such as browsing the web, manipulating files, and controlling graphical applications. BoxLite provides a unified interface for mouse control, keyboard input, screenshot capture, and scrolling within a virtual Ubuntu desktop. It is ideal for use cases requiring secure and isolated computer interactions, with inputs including API commands and outputs including screenshots and application responses.

Canonical page: https://skillsregistry.net/skills/boxlite-computer-use  
JSON: https://api.skillsregistry.net/v1/skills/boxlite-computer-use

## Description

Provides computer use capabilities through an isolated Ubuntu desktop sandbox environment, implementing Anthropic's computer use API for safe AI agent interaction with desktop applications. Built on the BoxLite sandboxing library, it exposes a unified 'computer' tool that enables mouse control, keyboard input, screenshot capture, and scrolling within a 1024x768 XFCE desktop environment. Designed for AI agents that need to interact with graphical applications, browse the web, or manipulate files while maintaining complete isolation from the host system through hardware-level VM virtualization.

## Trust

- **Trust score (0–1):** 0.76
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/boxlite-computer-use)
- **Repository:** <https://github.com/boxlite-ai/boxlite-mcp>

## 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": "boxlite-computer-use"
    }
  }
}
```

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