arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07473cs.CRcs.AI
收藏

给予一寸,他们将索取一英里:理解和测量基于MCP的AI系统中的调用者身份混淆

Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems

Institute for Clarity in Documentation(清晰文档研究所);Inria Paris-Rocquencourt(巴黎-罗克Quantin 研究院);Rajiv Gandhi University(拉朱·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕勒尔研究实验室);Shandong University(山东省大学);City University of Hong Kong(香港城市大学)

Yuhang Huang, Boyang Ma, Biwei Yan, Xuelong Dai, Yechao Zhang, Minghui Xu, Kaidi Xu, Yue Zhang

AI总结:

研究发现基于MCP的AI系统因缺乏调用者身份验证和细粒度授权而存在安全风险,需改进认证机制以减少攻击面。

摘要:

模型上下文协议(MCP)是一种开放且标准化的接口,使大语言模型(LLMs)能够与外部工具和服务交互,并越来越多地被AI代理采用。然而,基于MCP的系统的安全性仍 largely 未被探索。在本工作中,我们对集成在MCP客户端中的MCP服务器进行了大规模的安全分析。我们表明,将MCP服务器视为受信任实体而不验证调用者的身份是根本不安全的。由于MCP服务器通常无法区分谁在调用请求,一个授权决定可能隐式地允许多个潜在不信任的调用者。我们的实证研究发现,大多数MCP服务器依赖于持久化的授权状态,允许在初始授权后无需重新认证即可调用工具,无论调用者是谁。此外,许多MCP服务器未能在每种工具级别上执行认证,允许未经授权访问敏感操作。这些发现表明,一次性授权和服务器级信任显著扩大了基于MCP系统的攻击面,突显了需要显式调用者认证和细粒度授权机制的必要性。

英文摘要:

The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based systems remains largely unexplored.In this work, we conduct a large-scale security analysis of MCP servers integrated within MCP clients. We show that treating MCP servers as trusted entities without authenticating the caller identity is fundamentally insecure. Since MCP servers often cannot distinguish who is invoking a request, a single authorization decision may implicitly grant access to multiple, potentially untrusted callers.Our empirical study reveals that most MCP servers rely on persistent authorization states, allowing tool invocations after an initial authorization without re-authentication, regardless of the caller. In addition, many MCP servers fail to enforce authentication at the per-tool level, enabling unauthorized access to sensitive operations.These findings demonstrate that one-time authorization and server-level trust significantly expand the attack surface of MCP-based systems, highlighting the need for explicit caller authentication and fine-grained authorization mechanisms.

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。

↑