Give Mcp Agents Disposable Code Execution Sandboxes With Opensandbox Mcp

Name: Give Mcp Agents Disposable Code Execution Sandboxes With Opensandbox Mcp
Author: agentskillexchange

BSecurity

Expose sandbox creation, command execution, and file operations to MCP-capable agents so they can run untrusted code inside disposable Docker or Kubernetes-backed runtimes.

36 stars
0 votes
0 copies
1 view
Added June 8, 2026

ai-agentsjavascripttypescriptpythonrustgojavakotlinc#bashdocker

Works with

claude code
cursor
terminal
cli
api
mcp

Security analysis

B84/100

mediumInstalls packages at runtime which could introduce malicious dependencies
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned June 8, 2026

npx -y skills add agentskillexchange/skills --skill give-mcp-agents-disposable-code-execution-sandboxes-with-opensandbox-mcp --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Give Mcp Agents Disposable Code Execution Sandboxes With Opensandbox Mcp?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Give Mcp Agents Disposable Code Execution Sandboxes With Opensandbox Mcp

[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/agentskillexchange-give-mcp-agents-disposable-code-execution-sandboxe/badge)](https://www.skillsdirectory.com/skills/agentskillexchange-give-mcp-agents-disposable-code-execution-sandboxe)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: "Give MCP agents disposable code execution sandboxes with OpenSandbox MCP"
slug: "give-mcp-agents-disposable-code-execution-sandboxes-with-opensandbox-mcp"
description: "Expose sandbox creation, command execution, and file operations to MCP-capable agents so they can run untrusted code inside disposable Docker or Kubernetes-backed runtimes."
github_stars: 10207
verification: "security_reviewed"
source: "https://github.com/alibaba/OpenSandbox"
author: "Alibaba"
publisher_type: "organization"
category: "Security & Verification"
framework: "MCP"
tool_ecosystem:
  github_repo: "alibaba/OpenSandbox"
  github_stars: 10207
---

# Give MCP agents disposable code execution sandboxes with OpenSandbox MCP

Expose sandbox creation, command execution, and file operations to MCP-capable agents so they can run untrusted code inside disposable Docker or Kubernetes-backed runtimes.

## Prerequisites

Docker for local runtime or Kubernetes for cluster runtime, plus an MCP-capable client such as Claude Code or Cursor.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install opensandbox
- npm install @alibaba-group/opensandbox
- pip install opensandbox-cli
- uv tool install opensandbox-cli

Requirements and caveats from upstream:
- OpenSandbox is a **general-purpose sandbox platform** for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agents, Agent Evaluat...
- **Multi-language SDKs**: Provides sandbox SDKs in Python, Java/Kotlin, JavaScript/TypeScript, C#/.NET, Go.
- **Sandbox Runtime**: Built-in lifecycle management supporting Docker and [high-performance Kubernetes runtime](./kubernetes), enabling both local runs and large-scale distributed scheduling.

Basic usage or getting-started notes:
- OpenSandbox also provides osb, a terminal CLI for the common sandbox workflow: create sandboxes, run commands, move files, inspect diagnostics, and manage runtime egress policy.
- bash
- # or

- Source: https://github.com/alibaba/OpenSandbox
- Extracted from upstream docs: https://raw.githubusercontent.com/alibaba/OpenSandbox/HEAD/README.md

## Documentation

- https://open-sandbox.ai

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/give-mcp-agents-disposable-code-execution-sandboxes-with-opensandbox-mcp/)