用风险层级自动授权，让用户只在必要时做决定。
Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
- 基于风险层级自动允许安全调用，仅对高危操作提请确认。
- 实测98.2%准确率，99.4%风险升级被捕捉，验证开销仅8.2毫秒。
- 用户测试中更受青睐，信任感提升且减少重复确认。
随着模型上下文协议（MCP）的普及，通过有意义的用户许可来保障工具调用的安全性成为关键挑战。现有方法要么采用宽泛的开关控制，要么依赖不透明的LLM决策，无法识别危险参数，常导致许可疲劳。本文提出Conleash，一种客户端中间件，通过风险层级实现边界范围内的授权：自动允许已知安全调用，对高风险操作进行升级；配备用户自定义不变量的策略引擎，以及将用户决策转化为可复用规则的精炼循环。在984个真实调用轨迹上评估显示，Conleash准确率达98.2%，捕获99.4%的高风险升级，策略验证额外开销仅为8.2毫秒；用户研究（N=16）表明，参与者显著偏好其细粒度权限管理，认为更可信、提示更少。
原文摘要 · Abstract (English)
As Model Context Protocol adoption grows, securing tool invocations via meaningful user consent has become a critical challenge, as existing methods, broad always allow toggles or opaque LLM-based decisions, fail to account for dangerous call arguments and often lead to consent fatigue. In this work, we present Conleash, a client-side middleware that enforces boundary-scoped authorization by utilizing a risk lattice to auto-permit safe calls within known boundaries while escalating risks, a policy engine for user-defined invariants, and a refinement loop that converts user decisions into reusable rules. Evaluated on 984 real-world traces, Conleash achieved 98.2% accuracy, caught 99.4% of escalations, and added only 8.2 ms of overhead for policy verification; furthermore, in a user study where N=16, participants significantly preferred Conleash scoped permissions over traditional methods, citing higher trust and reduced prompting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。