Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913115522727936 |
|---|---|
| author | Li, Ying Chen, Yanju Wang, Peiran Khabra, Issac Shezan, Faysal Hossain Feng, Yu Tian, Yuan |
| author_facet | Li, Ying Chen, Yanju Wang, Peiran Khabra, Issac Shezan, Faysal Hossain Feng, Yu Tian, Yuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11360 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization Li, Ying Chen, Yanju Wang, Peiran Khabra, Issac Shezan, Faysal Hossain Feng, Yu Tian, Yuan Cryptography and Security Artificial Intelligence Software Engineering 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. |
| title | Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization |
| topic | Cryptography and Security Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2605.11360 |