Papers

论文:MCP 智能体存在工具提供方误绑定风险,五个客户端均受影响

When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

Why we picked it

搞 MCP 智能体开发的人应该看看这篇。它演示了攻击者只靠搭一个假 MCP 服务器、写好工具名和描述,就能在五个客户端里劫持工具调用。比一般的提示注入更隐蔽,因为宿主机和 LLM 本身都没被碰。如果你在拼多服务器的工具,这篇直接指出信任模型哪里有洞。

arXiv 论文(编号 2611.21577)提出"工具提供方误绑定"(tool-provider misbinding)这一新攻击面:攻击者不入侵宿主机、LLM、合法服务器或网络信道,只需运行另一个 MCP 服务器,用自选的元数据广播同名或相似工具,即可让请求被解析到攻击者控制的工具。

Body

论文将这一问题形式化为攻击者控制的工具选择优化问题,并在受控 MCP 环境中评测了五个基于 LLM 的客户端。实验显示误绑定由多个因素叠加驱动:精确名称碰撞、任务对齐的描述与兼容 schema 三者同时出现时失败最严重;

即便没有名称碰撞,带有权威措辞的描述加兼容 schema 也能导致错误提供方执行或提供方歧义无法解析。不同模型对同一绑定弱点表现不同,包括攻击者控制的选择、主动澄清请求、以及不稳定或不一致的提供方解析。

这暴露出 MCP 只标准化工具交互、却未将工具元数据绑定到可验证提供方身份的缺口。对开发多服务器 MCP 客户端的团队而言,工具发现的信任模型需要重新设计。

Original · arXiv cs.AI

When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. However, tool metadata used for discovery and selection is not, by itself, necessarily bound to a verified provider identity. This paper studies this gap as tool-provider misbinding: a failure in which a request intended for a legitimate provider is instead resolved to an attacker-controlled tool. The attacker does not compromise the host, LLM, legitimate server, or network channel; it only operates another MCP server that advertises tools with chosen metadata. We formulate tool provider misbinding as an attacker-controlled tool-selection optimization problem and evaluate it in a controlled MCP environment across five LLM-based clients. The results show that interactions drive misbinding. The strongest failures occur when exact-name collision, task-aligned description, and compatible schema reinforce one another, but authority-enhanced descriptions with compatible schema can also cause wrong-provider execution or unresolved provider ambiguity without name collision. Different models expose the same provider-binding weakness differently, including attacker-controlled provider selection, clarification requests, and unstable or inconsistent provider resolution.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include MCP and tools, agents, AI safety, LLM.

Source attribution: curated from arXiv cs.AI (@Zeynab Anbiaee, Sajjad Dadkhah, Ali A. Ghorbani).