Graph-Based Representation of Infrastructure as Code: Enabling Semantic Reasoning for Containerized Systems
Abstract
This paper proposes a new framework that integrates an ontology-based Knowledge Graph with the Model Context Protocol (MCP) for the semantic management of containerized infrastructures. The framework addresses a gap in orchestration platforms by providing a unified semantic representation of the topology, powered by an Extraction, Transformation, and Loading (ETL) process that analyzes Docker Compose files and makes the knowledge available to Large Language Models via a tool layer. This approach enables users to perform natural language queries to obtain deep insights into infrastructure configuration. The approach was validated through a controlled experiment simulating a DevOps scenario, in which the system successfully identified volume integrity failures and lateral movement risks—issues that traditional analysis would likely struggle to detect. The results demonstrate the framework’s superiority in automated auditing and conflict detection, bridging the gap between raw Infrastructure-as-Code artifacts and dynamic system reasoning for more intelligent and explainable container management.
References
Claise, B. (2025). Knowledge graph as preparation for llms, the logical next step in networking data modeling! –benoît claise. Online: [link]. Accessed: 2026-01-26.
Docker (2025). Docker. Online: [link]. Accessed: 2025-11-26.
Gruber, T. R. (1993). A translation approach to portable ontology specifications. Knowledge Acquisition, 5(2):199–220.
IBM and Stryker, C. (2023). What are large language models (llms)? Online: [link].
Kerner, S. M. (2025). Rise of containers: How enterprises are adapting to cloud-native demands. Online: [link]. Accessed: 2026-01-19.
Kyriakopoulos, K. G., Chilton, P., and Parish, D. (2015). Flowstats: An ontology based network management tool. In Proceedings of the International Conference on Computing Technology and Information Management (ICCTIM), pages 13–18. Accessed: 2025-08-08.
Martinez-Casanueva, I. D. (2025). Knowledge graphs for yang-based network management. Online: [link]. Accessed: 2025-11-26.
Nutanix (2025). Nutanix enterprise cloud index. Online: [link]. Accessed: 2026-01-28.
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., and Wu, X. (2024). Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
Red Hat (2025). What are large language models? Online: [link].
Shool, S., Adimi, S., Amleshi, R. S., Bitaraf, E., Golpira, R., and Tara, M. (2025). A systematic review of large language model (llm) evaluations in clinical medicine. BMC Medical Informatics and Decision Making, 25.
Simić, A. and Palma, D. (2024). Using knowledge graphs to automate network compliance of containerized services. In 2024 20th International Conference on Network and Service Management (CNSM), pages 1–5.
Singhal, A. (2012). Introducing the knowledge graph: Things, not strings. Online: [link]. Accessed: 2026-01-26.
Studer, R., Benjamins, V. R., and Fensel, D. (1998). Knowledge engineering: Principles and methods. Data & Knowledge Engineering, 25(1-2):161–197.
Vasileiou, Z., Kumara, I., Meditskos, G., Tokmakov, K., Radolović, D., Cruz, J., Nitto, E., Tamburri, D., Heuvel, W.-J., and Vrochidis, S. (2025). A knowledge-based approach for guided development of infrastructure as code. Software and Systems Modeling, pages 1–34.
Wang, W. et al. (2026). PTFusion: LLM-driven context-aware knowledge fusion for web penetration testing. Information Fusion, 127:103731.
Wu, S., Irsoy, O., Lu, S., Dabravolski, V., Dredze, M., Gehrmann, S., Kambadur, P., Rosenberg, D. S., and Mann, G. (2023). Bloomberggpt: A large language model for finance. ArXiv, abs/2303.17564.
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., and Zhang, Y. (2024). A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. High-Confidence Computing, 4:100211.
Zhou, H., Hu, C., Yuan, Y., Cui, Y., Jin, Y., Chen, C., Wu, H., Yuan, D., Jiang, L., Wu, D., Liu, X., Zhang, J., Wang, X., and Liu, J. (2025). Large language model (llm) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities. IEEE Communications Surveys & Tutorials, 27(3):1955–2005.
Zhou, J. et al. (2020). DockerKG: A knowledge graph of docker artifacts. In Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops, pages 367–372. Accessed: 2025-11-25.
