arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.21641cs.CRcs.SE
收藏

对过度授权工具能力的MCP服务器审计

Auditing MCP Servers for Over-Privileged Tool Capabilities

New York Institute of Technology(纽约理工学院)

Charoes Huang, Xin Huang, Amin Milani Fard

AI总结:

本文提出mcp-sec-audit工具,通过静态匹配和动态沙箱模糊测试评估MCP服务器的安全性,检测危险能力并提供缓解建议。

摘要:

模型上下文协议(MCP)已成为连接大语言模型(LLMs)与外部工具和数据的标准。然而,MCP服务器经常暴露特权功能,如文件系统访问、网络请求和命令执行,若未妥善保护可能被利用。我们提出了mcp-sec-audit,一种专门针对MCP服务器的安全评估工具包。它实现了针对Python基于MCP服务器的静态模式匹配,并通过Docker和eBPF进行动态沙箱模糊测试和监控。该工具通过可配置的基于规则的分析检测危险能力,并提供缓解建议。

英文摘要:

The Model Context Protocol (MCP) has emerged as a standard for connecting Large Language Models (LLMs) to external tools and data. However, MCP servers often expose privileged capabilities, such as file system access, network requests, and command execution that can be exploited if not properly secured. We present mcp-sec-audit, an extensible security assessment toolkit designed specifically for MCP servers. It implements static pattern matching for Python-based MCP servers and dynamic sandboxed fuzzing and monitoring via Docker and eBPF. The tool detects risky capabilities through configurable rule-based analysis and provides mitigation recommendations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑