# sandbox-mcp

> sandbox-mcp — leovilhena-sandbox-mcp. Use this tool when you need to securely execute code and fetch web data while preventing prompt injection and data exfiltration. The sandbox-mcp tool splits these tasks into isolated containers, ensuring that code execution and network access are separated to prevent security breaches. It is ideal for use cases where sensitive data is involved and security is a top priority.

Canonical page: https://skillsregistry.net/skills/leovilhena-sandbox-mcp  
JSON: https://api.skillsregistry.net/v1/skills/leovilhena-sandbox-mcp

## Description

Policy-driven MCP servers that split web fetching and code execution into isolated containers, preventing prompt injection and data exfiltration by ensuring neither can both execute code and reach the network.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hhcvw7t8fd)
- **Repository:** <https://github.com/Leovilhena/sandbox-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": "leovilhena-sandbox-mcp"
    }
  }
}
```

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