The week's pick
Reseach Article
Agentic Intelligence in Motion: Transforming Enterprise Data Movement with MCP on Cloud-Native Architectures
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 110 |
| Year of Publication: 2026 |
| Authors: Raghava Chellu |
10.5120/ijca9229b808fc12
|
Raghava Chellu . Agentic Intelligence in Motion: Transforming Enterprise Data Movement with MCP on Cloud-Native Architectures. International Journal of Computer Applications. 187, 110 ( May 2026), 45-50. DOI=10.5120/ijca9229b808fc12
Abstract
Traditional Extract-Transform-Load (ETL) pipelines have led to serious issues in enterprise data movement, such as high latency, inability to provide real-time responsiveness, and the inability to efficiently process complex and heterogeneous data sources. As data is exponentially rising and the demand to have real-time analytics is rising, intelligent, scalable and automated solutions are required. I will propose a new framework in the current paper, which is the combination of the Agentic Artificial Intelligence with the Model Context Protocol (MCP) that will help to create the dynamic and context-responsive flow of data. The framework has been built with the latest technology, such as Google Gemini to make intelligent decisions, and cloud-native technology, such as Kubernetes, Docker, and Google Cloud Run, to scale to any size. Such interactions as Agent-to-Agent (A2A) and Agent-to-User Interface (A2UI) can be used to achieve autonomous coordination and interaction with users. The experimental evaluation confirms that the provided system will be able to reduce the latency by half, expand scalability because of the dynamism of resource allocation, and make operations more efficient. The study contributes to a coherent, cloud-native system that transforms fixed data pipelines into dynamic and intelligent systems, which can be a plausible solution to the existing issues of data movements in enterprises.
References
- Prince Kumar, “Agentic ai-driven enterprise architecture: a foundational framework for scalable, secure, and resilient systems,” International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 4, Mar. 2025, doi: https://doi.org/10.22399/ijcesen.4210.
- K. Perikala, “Architecting MCP-Based Platforms for Enterprise-Scale Agentic Generative AI,” Journal of Business Intelligence and Data Analytics, vol. 2, no. 3, pp. 1–8, 2023, doi: https://doi.org/10.55124/jbid.v2i3.264.
- S. Chakraborty, “Data Stewardship Co-Pilot: Transforming Enterprise Data Governance with Generative AI and Agentic Frameworks,” European Journal of Computer Science and Information Technology, vol. 13, no. 20, pp. 1–15, Apr. 2025, doi: https://doi.org/10.37745/ejcsit.2013/vol13n20115.
- Dr. N. Sinha, “Building Trust in Agentic AI: TRACE Framework for Policy-Driven Multi-Agent System Design,” International Journal of Current Science Research and Review, vol. 09, no. 02, Feb. 2026, doi: https://doi.org/10.47191/ijcsrr/v9-i2-46.
- S. Prabhagaran, “Building Intelligent Workflows with the Model Context Protocol (MCP): Servers, Clients, and Extensible Tools,” Journal of Artificial Intelligence & Cloud Computing, vol. 4, no. 6, p. 10, Nov. 2025, doi: https://doi.org/10.47363/jaicc/techfusion2025/2025(4)10.
- L. G. Di Maggio, “Predictive Maintenance MCP: An Open-Source Framework for Bridging Large Language Models and Industrial Condition Monitoring via the Model Context Protocol,” Applied Sciences, vol. 16, no. 6, p. 2812, Mar. 2026, doi: https://doi.org/10.3390/app16062812.
- J. Sarkar and G. Agnihotram, “Model Context Protocol: The Central Nervous System for a New Generation of Artificially Intelligent Agents,” Scientific Journal of Computer Science, vol. 1, no. 2, pp. 84–93, Nov. 2025, doi: https://doi.org/10.64539/sjcs.v1i2.2025.327.
- J.-W. Ahn and H.-Y. Kwon, “Privacy Threats and Policy Responses to the Use of AI Agents : Focusing on the Model Context Protocol Environment,” Journal of Korean Institute of Intelligent Systems, vol. 35, no. 6, pp. 541–553, Dec. 2025, doi: https://doi.org/10.5391/jkiis.2025.35.6.541.
- Anand Laxman Mhatre, “Microservices Architecture Using Docker and Kubernetes,” International Journal For Multidisciplinary Research, vol. 5, no. 5, Oct. 2023, doi: https://doi.org/10.36948/ijfmr.2023.v05i05.12095.
- V. K. Adari, “Optimizing Cloud-Native Machine Learning Pipelines Using ARAS-Based Multi-Criteria Decision Analysis,” International Journal of Computer Science and Data Engineering, vol. 2, no. 4, pp. 1–7, 2025, doi: https://doi.org/10.55124/csdb.v2i4.256.
- C. Jeong, “A Practical MCP×A2A Integration Framework for Interoperability in LLM-Based Autonomous Multi-Agent Systems,” Journal of Intelligence and Information Systems, vol. 31, no. 3, pp. 141–170, Sep. 2025, doi: https://doi.org/10.13088/jiis.2025.31.10.141.
- C. Zhu, Mehdi Dastani, and S. Wang, “Correction: A survey of multi-agent deep reinforcement learning with communication,” Autonomous Agents and Multi-Agent Systems, vol. 38, no. 1, Mar. 2024, doi: https://doi.org/10.1007/s10458-024-09644-x.
- K. Jones, “Design of Scalable Architecture for Real-Time Parallel Computation of Long to Ultra-Long Real-Data DFTs,” Engineering: Open Access, vol. 2, no. 4, pp. 01-11, Nov. 2024, doi: https://doi.org/10.33140/eoa.02.04.04.
- D. Seenivasan, “Real-Time Data Processing with Streaming ETL,” International Journal of Science and Research (IJSR), vol. 12, no. 11, pp. 2185–2192, Nov. 2023, doi: https://doi.org/10.21275/sr24619000026.
- H. Tebourbi et al., “BPMN-Based Design of Multi-Agent Systems: Personalized Language Learning Workflow Automation with RAG-Enhanced Knowledge Access,” Information, vol. 16, no. 9, p. 809, Sep. 2025, doi: https://doi.org/10.3390/info16090809.
- Siva Prakash Bikka, “Modern Workflow Automation Architecture Patterns: Contemporary Design Approaches for Enterprise Digital Transformation,” Journal of Information Systems Engineering and Management, vol. 11, no. 2s, pp. 1507–1517, Feb. 2026, doi: https://doi.org/10.52783/jisem.v11i2s.14634.
- V. K. Malthummeda, “Agentic Leave and Dispatch Automation for Trucking Fleets Using MCP and LLMs,” International Journal of AI, BigData, Computational and Management Studies, vol. 7, no. 1, pp. 70–73, 2026, doi: https://doi.org/10.63282/3050-9416.ijaibdcms-v7i1p111.
- Dharam Pal Singh, “Adaptive Data Pipeline Architectures for Evolving Fraud Patterns Using Graph ML,” International Journal of Sustainability and Innovation in Engineering, vol. 4, no. 1, Mar. 2026, doi: https://doi.org/10.56830/ijsie202603.
- N. Gupta and S. Heggond, “Agentic artificial intelligence-driven tutoring: A multi-agent cognitive architecture for personalized adaptive learning in Education,” International Journal of Applied Resilience and Sustainability, vol. 2, no. 2, pp. 572–598, Feb. 2026, DOI: https://doi.org/10.70593/deepsci.0202022.
Index Terms
Keywords