# gbox

> Use this tool when you need to integrate and test AI agents or MCP systems in a secure and isolated environment. The gbox sandbox provides a self-hostable solution for safely containing and evaluating AI agent interactions, solving problems related to security, testing, and development. It accepts AI agent or MCP integration inputs and outputs test results and performance metrics through a customizable interface.

Canonical page: https://skillsregistry.net/skills/babelcloud-gru-sandbox  
JSON: https://api.skillsregistry.net/v1/skills/babelcloud-gru-sandbox

## Description

Gru-sandbox(gbox) is an open source project that provides a self-hostable sandbox for MCP integration or other AI agent usecases.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-07

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bhy7nhkq3s)
- **Repository:** <https://github.com/babelcloud/gbox>

## 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": "babelcloud-gru-sandbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/babelcloud-gru-sandbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/babelcloud-gru-sandbox/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