No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by agent-infra · MCP Server · ★ 5.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sandbox safe to install? View the security audit →
AIO Sandbox - All-in-One Agent Sandbox Environment 🌐 Browser 🤖 MCP 🌐 Website   |   🔌 API   |   📑 Paper   |   🌟 Examples   |   📊 Evaluation    🚀 Quick Start Get up and running in 30 seconds: bash doc
| Stars | 5,908 |
| Forks | 530 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 63.9845774529889/100 |
| Open Issues | 71 |
| Last Updated | 2026-09-14 |
| Created | 2025-08-06 |
| Platforms | browser, docker, mcp, python, vscode |
| Est. Tokens | ~16k |
These tools work well together with sandbox for enhanced workflows:
Looking for a sandbox alternative? If you're comparing sandbox with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Personal memory across agents
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API k
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabil
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling s
Model Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real
Explore other popular mcp server tools:
sandbox is All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.. It is categorized as a MCP Server with 5.9k GitHub stars.
sandbox is primarily written in Python. It covers topics such as agent, all-in-one, browser.
You can find installation instructions and usage details in the sandbox GitHub repository at github.com/agent-infra/sandbox. The project has 5.9k stars and 530 forks, indicating an active community.
sandbox is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to sandbox on Agent Skills Hub include memU, nanobrowser, claude-context. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: