Trust-as-a-Service: Intelligent Collaboration Orchestration via Model Context Protocol-Aided Agentic AI

As future networked systems increasingly rely on collaborative task execution among distributed devices, trust becomes essential for identifying reliable collaborators whose capabilities and resources match task-specific needs. However, diverse task needs, limited task-owner knowledge, and complex inter-device relationships make it challenging to evaluate the trustworthiness of potential collaborators and to select suitable collaborators for task completion. To address these challenges, this paper proposes Trust-as-a-Service (TaaS), an intelligent collaboration orchestration paradigm that enables trust evaluation and collaborator selection to be autonomously tailored to different task needs. To realize TaaS, we develop a Model Context Protocol (MCP)-aided agentic AI framework. The central server-side agent autonomously performs trust-related operations according to task-specific needs and delivers trust assessment services to task owners through a unified interface. Meanwhile, device-side agents expose their capabilities and resources via MCP servers, allowing devices to be dynamically discovered, evaluated, engaged, and released to form task-specific collaborative units. Experimental results demonstrate that the proposed TaaS achieves 100% collaborator selection accuracy, along with high reliability and resource-efficient task completion.