Authors : Ameek Sharma; Anirudh Sharma; Muskan Gyanani; Bersha Kumari; Madhu Choudhary

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/yc5ssm8n

Scribd : https://tinyurl.com/mrx2drrz

DOI : https://doi.org/10.38124/ijisrt/26apr198

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : New complexity introduced to enterprise networks drives demand for advanced diagnostic tools that can not only quickly parse device configurations and detect misconfigurations, but also recommend remedies. Network troubleshooting in traditional environments is still a manual, time-consuming process that relies heavily on expert knowhow. In this paper, we present a new architecture for an Intelligent Network Troubleshooting Assistant that automates the entire end-to-end diagnostic pipeline. It uses a multi-stage parsing engine that can parse heterogeneous Cisco IOS outputs, a deterministic rule engine to match against eight classes of misconfigurations, produces a weighted health score and associated fix plan. The system architecture was inspired by the Model Context Protocol (MCP) and microservices architecture, where its modularization, scalability, and educational purpose among other design principles were taken into consideration. A multi-device, complex-network, case study validates our system's ability to detect root-cause issues accurately and produce educational insights and actionable remediation steps. Our findings indicate that the architecture not only lowers mean-time-to-resolution (MTTR) for network problems but also acts as a tool to teach budding network engineers.

Keywords : Network Troubleshooting, Cisco IOS, Rule-Based Systems, Health Scoring, Educational Technology, Microservices, Model Context Protocol.

References :

1. S. Das, A. K. Saha, and P. K. Dhar, “Network Troubleshooting: A Survey of Tools and Techniques,” International Journal of Computer Applications, vol. 182, no. 38, pp. 1–6, Jan. 2019.
2. J. Kurose and K. Ross, Computer Networking: A Top-Down Approach, 8th ed. Pearson, 2020.
3. InfoQ, “MCP: the Universal Connector for Building Smarter, Modular AI Agents,” 2025. [Online]. Available: https://www.infoq.com/articles/model-context-protocol/
4. ISO/IEC 7498-4, Information processing systems – Open Systems Interconnection – Basic Reference Model – Part 4: Management framework, 1989.
5. S. V. K. Chaitanya, “Automation in Network Troubleshooting Using Python,” International Journal of Research in Engineering and Science, vol. 10, no. 5, pp. 43–48, May 2022.
6. K. Byers, “A Practical Approach to Network Automation,” Cisco Press, 2019.
7. F. G. N. A. Almeida, “Machine Learning for Network Management: A Survey,” IEEE Communications Surveys & Tutorials, vol. 23, no. 3, pp. 1884–1913, Third Quarter 2021.
8. P. Jackson, Introduction to Expert Systems, 3rd ed. Addison-Wesley, 1999.
9. Hou, Y. Zhao, S. Wang, and H. Wang, “Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions,” arXiv preprint arXiv:2503.23278, 2025.