by BIGPPWONG · MCP Server · ★ 212
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 212 |
| Forks | 26 |
| Language | TypeScript |
| Category | MCP Server |
| License | GPL-3.0 |
| Quality Score | 64/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-22 |
| Created | 2025-09-12 |
| Platforms | browser, cli, mcp, node |
| Est. Tokens | ~1878k |
EdgeBox - The Local Desktop Sandbox for AI Agents 💡 新项目推荐: 如果你需要更轻量化的内核级沙箱方案,查看 DAIMON —— 一个专为 AI Agent 设计的轻量级本地沙箱运行时。DAIMON 采用 Rust 编写,基于 Linux Landlock LSM 和 seccomp 实现 OS 内核级强制沙箱,提供细粒度的文件系统访问控制、网络隔离和非特权用户身份执行。相比传统 Docker 容器方案更加轻量,适合 MCP Server 的安全执行环境。 A fully-featured, GUI-powered local LLM Agent sandbox with complete support for the MCP protocol.
These tools work well together with EdgeBox for enhanced workflows:
Looking for a EdgeBox alternative? If you're comparing EdgeBox 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.
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with fil
Shell and coding agent on mcp clients
Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - imple
A simple Python sandbox for helpful LLM data agents
Drive a real, stock iPhone (and any macOS app) from any MCP client via iPhone Mirroring — no Developer Mode, n
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: