Adaptive Model Context Protocols for Trustworthy and Secure Agentic AI Systems
DOI:
https://doi.org/10.15680/IJCTECE.2025.0805020Keywords:
Adaptive Model Context Protocols (AMCP), Agentic AI, Trustworthiness Index, ., Context Adaptation Time, Federated Adversarial Security, Bayesian Trust Estimation, Meta-LearningAbstract
The Adaptive Model Context Protocols Framework, the proposed AMCP Framework, offers a reliable, safe, and flexible system on which agentic AI can perform based on multi-context settings. The model offers context sensitivity and operational integrity wherein context-aware meta-learning and Bayesian trust estimation, zero-trust security, and federated adversarial defense management are implemented. The performance of the model has been greatly improved as indicated by the results gained after the tests run after 20 training epochs. The accuracy was in the range of 0.71-0.93, the precision was 0.69-0.91 and the recall was 0.66-0.89. The fact that the F1-score consistently converged at 0.90 confirmed dynamic learning, which is balanced understanding of context and policy adaptation and adaptation efficiency of 0.78 to 0.92. In general, they show that the AMCP framework can ensure that the AI responds in a safe and sensitive way depending on its surroundings. It is also able to support clear-cut decision making which is rather essential to autonomous and ethical stable AI systems.
References
[1]. Vanneste, Bart S., and Phanish Puranam. "Artificial intelligence, trust, and perceptions of agency." Academy of Management Review ja (2024): amr-2022.
[2]. GOPALAKRISHNA, KARAMCHAND. "Zero trust and AI: A synergistic approach to next-generation cyber threat mitigation." WORLD 24, no. 3 (2024): 3374-3387.
[3]. Conradie, Niël Henk, and Saskia K. Nagel. "No agent in the machine: Being trustworthy and responsible about AI." Philosophy & Technology 37, no. 2 (2024): 72.
[4]. Freiman, Ori. "Making sense of the conceptual nonsense ‘trustworthy AI’." AI and Ethics 3, no. 4 (2023): 1351-1360.
[5]. Manish Hatwalne et al., “https://www.redpanda.com/blog/what-is-agentic-ai-introduction-autonomous-agents
[6]. Lahusen, Christian, Martino Maggetti, and Marija Slavkovik. "Trust, trustworthiness and AI governance." Scientific Reports 14, no. 1 (2024): 20752.
[7]. Pakina, Anil Kumar, Ashwin Sharma, and Mangesh Pujari. "AI Governance via Explainable Reinforcement Learning (XRL) for Adaptive Cyber Deception in Zero-Trust Networks." (2024).
[8]. Mintoo, Abdul Awal, Abu Saleh Muhammad Saimon, Mohammed Majid Bakhsh, and Marjina Akter. "NATIONAL RESILIENCE THROUGH AI-DRIVEN DATA ANALYTICS AND CYBERSECURITY FOR REAL-TIME CRISIS RESPONSE AND INFRASTRUCTURE PROTECTION." American Journal of Scholarly Research and Innovation 1, no. 01 (2022): 137-169.
[9]. ADABARA, IBRAHIM, Bashir Olaniyi Sadiq, Aliyu Nuhu Shuaibu, Yale Ibrahim Danjuma, and Venkateswarlu Maninti. "Trustworthy agentic AI systems: a cross-layer review of architectures, threat models, and governance strategies for real-world deployment." F1000Research 14 (2025): 905.
[10]. Ahmadi, Sina. "Autonomous Identity-Based Threat Segmentation for Zero Trust Architecture." Cyber Security and Applications (2025): 100106.
[11]. Vatsa, Adarsh, Pratyush Patel, and William Eiers. "Synthesizing Access Control Policies using Large Language Models." In 2025 IEEE/ACM International Workshop on Natural Language-Based Software Engineering (NLBSE), pp. 13-16. IEEE, 2025.
[12]. Moharir, Chandrashekhar, Sharad Shyam Ojha, and Amit Choudhury. "Contextual AI Models for Adaptive Data Classification and Access Control." (2025).
[13]. Kumar, Arun, Neeran Karnik, and Girish Chafle. "Context sensitivity in role-based access control." ACM SIGOPS Operating Systems Review 36, no. 3 (2002): 53-66.
[14]. Kalaria, Rudri, A. S. M. Kayes, Wenny Rahayu, Eric Pardede, and Ahmad Salehi Shahraki. "Adaptive context-aware access control for IoT environments leveraging fog computing." International Journal of Information Security 23, no. 4 (2024): 3089-3107.
[15]. A. Dorri, S. S. Kanhere, and R. Jurdak, “Multi-agent systems: A survey,” IEEE Access, vol. 6, pp. 28573–28593, 2018.
[16]. S. V. Albrecht and P. Stone, “Autonomous agents modelling other agents: A comprehensive survey and open problems,” Artificial Intelligence, vol. 258, pp. 66–95, 2018.
[17]. B. Hayes and J. A. Shah, “Improving robot controller transparency through autonomous policy explanation,” Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction, pp. 303–312, 2017.
[18]. A. Lazaridou and M. Baroni, “Emergent multi-agent communication in the deep learning era,” arXiv:2006.02419, 2020.
[19]. J. Foerster, I. A. Assael, N. de Freitas, and S. Whiteson, “Learning to communicate with deep multi-agent reinforcement learning,” Advances in Neural Information Processing Systems, pp. 2137–2145, 2016.
[20]. R. Lowe, Y. Wu, A. Tamar, J. Harb, P. Abbeel, and I. Mordatch, “Multi-agent actor-critic for mixed cooperative-competitive environments,” Advances in Neural Information Processing Systems, pp. 6379–6390, 2017.
[21]. M. Müller, F. Hadfi, A. Ratli, and G. Nájera, “Agentic AI: A research agenda for the next generation of intelligent systems,” Artificial Intelligence, vol. 321, pp. 103947, 2023.
[22]. J. Park, N. Bhattacharjee, and C. Li, “Communication protocols for LLM-based multi-agent systems,” Proceedings of the Conference on Neural Information Processing Systems, pp. 3241–3255, 2024.
[23]. Ravi Kiran, Mahesh Reddy Konatham, Dharmateja Priyadarshi Uddandaraohttps://www.researchgate.net/publication/392557837_Adaptive_Model_Context_Protocols_for_Multi-Agent_Collaboration(2025).
[24]. Krishnan, Naveen. "Advancing multi-agent systems through model context protocol: Architecture, implementation, and applications." arXiv preprint arXiv:2504.21030 (2025).
[25]. Moharir, Chandrashekhar, Sharad Shyam Ojha, and Amit Choudhury. "Contextual AI Models for Adaptive Data Classification and Access Control." (2025).
[26]. Hou, Xinyi, Yanjie Zhao, Shenao Wang, and Haoyu Wang. "Model context protocol (mcp): Landscape, security threats, and future research directions." arXiv preprint arXiv:2503.23278 (2025).
[27]. Nishad, Dinesh Kumar, Vandna Rani Verma, Pushkar Rajput, Sandeep Gupta, Anurag Dwivedi, and Dharti Raj Shah. "Adaptive AI-enhanced computation offloading with machine learning for QoE optimization and energy-efficient mobile edge systems." Scientific Reports 15, no. 1 (2025): 15263.
[28]. Xu, Haowen, Yulin Sun, Jose Tupayachi, Olufemi Omitaomu, Sisi Zlatanova, and Xueping Li. "Towards the autonomous optimization of urban logistics: Training generative ai with scientific tools via agentic digital twins and model context protocol." arXiv preprint arXiv:2506.13068 (2025).
[29]. Vadisetty, Rahul, and Anand Polamarasetti. "AI-generated privacy-preserving protocols for cross-cloud data sharing and collaboration." In 2024 IEEE 4th International Conference on ICT in Business Industry & Government (ICTBIG), pp. 1-5. IEEE, 2024.
[30]. Narne, Suman, Tolu Adedoja, M. Mohan, and T. Ayyalasomayajula. "AI-driven decision support systems in management: enhancing strategic planning and execution." International journal on recent and innovation trends in computing and communication 12, no. 1 (2024): 268-276.
[31]. Bushigampala, Bharath Kumar, and Anil Chowdary Inaganti. "Threat Detection in Critical Infrastructure Using AI Models." International Journal of Acta Informatica 2, no. 1 (2023): 196-208.
[32]. Jordan Smith, Amelia Ethan. "Context-Aware AI-Augmented Access Control for Dynamic MFA Environments in Critical Infrastructure." (2023).
[33]. Shoaib, Mohamed R., Zefan Wang, Milad Taleby Ahvanooey, and Jun Zhao. "Deepfakes, misinformation, and disinformation in the era of frontier AI, generative AI, and large AI models." In 2023 international conference on computer and applications (ICCA), pp. 1-7. IEEE, 2023.
[34]. Reddy, Rajesh, Sonal Chopra, and Meena Singh. "Leveraging Transformer Models and Reinforcement Learning for Optimized AI-Enhanced Automated Sales Outreach." Innovative AI Research Journal 12, no. 1 (2023).
[35]. Haldorai, Anandakumar, Makarand Upadhyaya, G. Jawaharlal Nehru, and Dhiraj Kapila. "Self-Learning and Adaptive Networking Protocols and Algorithms for 6G Edge Nodes." In 2023 Fifth International Conference on Electrical, Computer and Communication Technologies (ICECCT), pp. 1-10. IEEE, 2023.
