# SandboxAPI

> Use this tool when you need to execute code in a secure and isolated environment, solving problems such as testing untrusted code, preventing data breaches, and ensuring consistent results. The SandboxAPI takes code inputs in various programming languages and returns execution outputs, providing a robust interface for single, batch, or parallel executions. It is ideal for use cases requiring temporary, network-isolated, and ephemeral filesystems, such as development, testing, and education.

Canonical page: https://skillsregistry.net/skills/sandboxapi  
JSON: https://api.skillsregistry.net/v1/skills/sandboxapi

## Description

Provides three tools for running code in isolated sandbox environments: single execution, batch parallel execution, and language listing. Uses gVisor-sandboxed Docker containers with network isolation and ephemeral filesystems, supporting Python, JavaScript, TypeScript, Go, Java, C++, C, and Bash. Built by SandboxAPI, the service provider behind the underlying execution infrastructure.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sandboxapi)
- **Repository:** <https://github.com/sandboxapi/sandboxapi-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": "sandboxapi"
    }
  }
}
```

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