Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
Ying Li, Yanju Chen, Peiran Wang, Issac Khabra, Faysal Hossain Shezan + 2 more
TLDR
Conleash is a client-side middleware that uses a risk lattice and policy engine to provide consent-driven, boundary-scoped authorization for MCP tool invocations.
Key contributions
- Introduces Conleash, a client-side middleware for consent-driven authorization in Model Context Protocol (MCP).
- Utilizes a risk lattice to auto-permit safe calls and escalate risks, preventing consent fatigue.
- Features a policy engine for user-defined invariants and a refinement loop for reusable authorization rules.
- Achieved 98.2% accuracy and 99.4% escalation detection with minimal overhead in real-world tests.
Why it matters
This paper addresses the critical challenge of securing tool invocations in MCP by offering a novel, user-centric authorization system. Conleash improves security by preventing dangerous calls and enhances user experience through reduced consent fatigue and higher trust. Its practical evaluation demonstrates high accuracy and efficiency.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.