Cloud Microservices: An Empirical Study of MCP-Orchestrated LLM Agents for Incident Triage
Resumo
Context: The growing complexity of cloud microservices imposes significant challenges for Site Reliability Engineering (SRE), contributing to delayed incident resolution and increased operational effort. Objective: This study evaluated the effectiveness of autonomous agents based on Large Language Models (LLMs), orchestrated via the Model Context Protocol (MCP), for root cause analysis in a cloud-native setting. Method: We conducted a controlled Randomized Complete Block Design (RCBD) experiment in Kubernetes with automated fault injection, covering three distinct failure scenarios and multiple LLM configurations across 360 executions. Results: A high-performing configuration (Gemini 2.5 Flash at low temperature) achieved a 71.1% root-cause identification success rate, substantially above a random-chance baseline (≈ 0.91%). Smaller models exhibited higher token and step volatility (CV = 2.17) and more repeated tool-call cycles, challenging the assumption that lower-parameter models are inherently more cost-effective for SRE workflows. Conclusion: The results provide empirical evidence that MCP-orchestrated LLM agents can support root cause analysis in cloud-native environments and offer practical guidance for model selection in AIOps/SRE workflows.
Referências
Bagehorn, F., Rios, J., Jha, S., Filepp, R., Shwartz, L., Abe, N., and Yang, X. (2022). A fault injection platform for learning AIOps models. In Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, pages 1–5, New York, NY, USA. ACM.
Colaço Júnior, M. (2025). IA para a Galera Toda: Agentes e Inovação Experimental Sem Código: Guia Prático para Dominar Prompts, Inovar, Criar Experimentos, Artigos e Lucrar com Agentes Inteligentes – Tudo Sem Programação. Amazon Publishing, Seattle, WA.
Colaço Júnior, M., Cruz, R. F., Araújo, L. V. d., Bliacheriene, A. C., and Nunes, F. d. L. S. (2022). Evaluation of a process for the experimental development of data mining, ai and data science applications aligned with the strategic planning. JISTEM - Journal of Information Systems and Technology Management, 19.
Jiang, Z., Huang, J., Yu, G., Chen, Z., Li, Y., Zhong, R., Feng, C., Yang, Y., Yang, Z., and Lyu, M. (2025). L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis, page 51–63. Association for Computing Machinery, New York, NY, USA.
Li, S., Wei, X., Yuan, J., Wang, X., and Miao, K. (2025). Secure model context protocol for large language models with dual signatures. In Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture, MobiArch ’25, page 1–6, New York, NY, USA. Association for Computing Machinery.
Pei, C., Wang, Z., Liu, F., Li, Z., Liu, Y., He, X., Kang, R., Zhang, T., Chen, J., Li, J., Xie, G., and Pei, D. (2025). Flow-of-action: Sop enhanced llm-based multi-agent system for root cause analysis. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 422–431, New York, NY, USA. Association for Computing Machinery.
Pham, L., Zhang, H., Ha, H., Salim, F., and Zhang, X. (2025). Rcaeval: A benchmark for root cause analysis of microservice systems with telemetry data. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 777–780, New York, NY, USA. Association for Computing Machinery.
Rombaut, B., Masoumzadeh, S., Vasilevski, K., Lin, D., and Hassan, A. E. (2025). Watson: A cognitive observability framework for the reasoning of llm-powered agents.
Severino, A. J. (2018). Metodologia do trabalho científico. Cortez, São Paulo, 24 edition.
Shetty, M., Chen, Y., Somashekar, G., Ma, M., Simmhan, Y., Zhang, X., Mace, J., Vandevoorde, D., Las-Casas, P., Gupta, S. M., Nath, S., Bansal, C., and Rajmohan, S. (2024). Building ai agents for autonomous clouds: Challenges and design principles. In Proceedings of the 2024 ACM Symposium on Cloud Computing, SoCC ’24, page 99–110, New York, NY, USA. Association for Computing Machinery.
Xiao, X., Gao, C., and Bogner, J. (2025). On the effectiveness of microservices tactics and patterns to reduce energy consumption: An experimental study on trade-offs. In 2025 IEEE 22nd International Conference on Software Architecture (ICSA), page 164–175. IEEE.
Xin, R., Chen, P., and Zhao, Z. (2023). Causalrca: Causal inference based precise fine-grained root cause localization for microservice applications. J. Syst. Softw., 203(C).
Xu, H., Wang, X., and Ji, S. (2025a). Reliable and efficient container orchestration of llms via mcp. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM ’25, page 6885–6886, New York, NY, USA. Association for Computing Machinery.
Xu, J., Zhang, Q., Zhong, Z., He, S., Zhang, C., Lin, Q., Pei, D., He, P., Zhang, D., and Zhang, Q. (2025b). OpenRCA: Can large language models locate the root cause of software failures? In The Thirteenth International Conference on Learning Representations.
Yang, N., Lyu, G., Ma, M., Lu, Y., Li, Y., Gao, Z., Ye, H., Zhang, J., Chen, T., and Chen, Y. (2025). Iot-mcp: Bridging llms and iot systems through model context protocol. In Proceedings of the ACM Workshop on Wireless Network Testbeds, Experimental Evaluation & Characterization, WiNTECH ’25, page 73–80, New York, NY, USA. Association for Computing Machinery.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023). React: Synergizing reasoning and acting in language models.
Zhang, L., Zhai, Y., Jia, T., Duan, C., He, M., Pan, L., Liu, Z., Ding, B., and Li, Y. (2025). Microremed: Benchmarking llms in microservices remediation.
Zheng, L., Chen, Z., He, J., and Chen, H. (2024). Mulan: Multi-modal causal structure learning and root cause analysis for microservice systems. In Proceedings of the ACM Web Conference 2024, WWW ’24, page 4107–4116, New York, NY, USA. Association for Computing Machinery.
Zota, R. D., Bărbulescu, C., and Constantinescu, R. (2025). A practical approach to defining a framework for developing an agentic AIOps system. Electronics (Basel), 14(9):1775.
Colaço Júnior, M. (2025). IA para a Galera Toda: Agentes e Inovação Experimental Sem Código: Guia Prático para Dominar Prompts, Inovar, Criar Experimentos, Artigos e Lucrar com Agentes Inteligentes – Tudo Sem Programação. Amazon Publishing, Seattle, WA.
Colaço Júnior, M., Cruz, R. F., Araújo, L. V. d., Bliacheriene, A. C., and Nunes, F. d. L. S. (2022). Evaluation of a process for the experimental development of data mining, ai and data science applications aligned with the strategic planning. JISTEM - Journal of Information Systems and Technology Management, 19.
Jiang, Z., Huang, J., Yu, G., Chen, Z., Li, Y., Zhong, R., Feng, C., Yang, Y., Yang, Z., and Lyu, M. (2025). L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis, page 51–63. Association for Computing Machinery, New York, NY, USA.
Li, S., Wei, X., Yuan, J., Wang, X., and Miao, K. (2025). Secure model context protocol for large language models with dual signatures. In Proceedings of the 20th Workshop on Mobility in the Evolving Internet Architecture, MobiArch ’25, page 1–6, New York, NY, USA. Association for Computing Machinery.
Pei, C., Wang, Z., Liu, F., Li, Z., Liu, Y., He, X., Kang, R., Zhang, T., Chen, J., Li, J., Xie, G., and Pei, D. (2025). Flow-of-action: Sop enhanced llm-based multi-agent system for root cause analysis. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 422–431, New York, NY, USA. Association for Computing Machinery.
Pham, L., Zhang, H., Ha, H., Salim, F., and Zhang, X. (2025). Rcaeval: A benchmark for root cause analysis of microservice systems with telemetry data. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 777–780, New York, NY, USA. Association for Computing Machinery.
Rombaut, B., Masoumzadeh, S., Vasilevski, K., Lin, D., and Hassan, A. E. (2025). Watson: A cognitive observability framework for the reasoning of llm-powered agents.
Severino, A. J. (2018). Metodologia do trabalho científico. Cortez, São Paulo, 24 edition.
Shetty, M., Chen, Y., Somashekar, G., Ma, M., Simmhan, Y., Zhang, X., Mace, J., Vandevoorde, D., Las-Casas, P., Gupta, S. M., Nath, S., Bansal, C., and Rajmohan, S. (2024). Building ai agents for autonomous clouds: Challenges and design principles. In Proceedings of the 2024 ACM Symposium on Cloud Computing, SoCC ’24, page 99–110, New York, NY, USA. Association for Computing Machinery.
Xiao, X., Gao, C., and Bogner, J. (2025). On the effectiveness of microservices tactics and patterns to reduce energy consumption: An experimental study on trade-offs. In 2025 IEEE 22nd International Conference on Software Architecture (ICSA), page 164–175. IEEE.
Xin, R., Chen, P., and Zhao, Z. (2023). Causalrca: Causal inference based precise fine-grained root cause localization for microservice applications. J. Syst. Softw., 203(C).
Xu, H., Wang, X., and Ji, S. (2025a). Reliable and efficient container orchestration of llms via mcp. In Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM ’25, page 6885–6886, New York, NY, USA. Association for Computing Machinery.
Xu, J., Zhang, Q., Zhong, Z., He, S., Zhang, C., Lin, Q., Pei, D., He, P., Zhang, D., and Zhang, Q. (2025b). OpenRCA: Can large language models locate the root cause of software failures? In The Thirteenth International Conference on Learning Representations.
Yang, N., Lyu, G., Ma, M., Lu, Y., Li, Y., Gao, Z., Ye, H., Zhang, J., Chen, T., and Chen, Y. (2025). Iot-mcp: Bridging llms and iot systems through model context protocol. In Proceedings of the ACM Workshop on Wireless Network Testbeds, Experimental Evaluation & Characterization, WiNTECH ’25, page 73–80, New York, NY, USA. Association for Computing Machinery.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023). React: Synergizing reasoning and acting in language models.
Zhang, L., Zhai, Y., Jia, T., Duan, C., He, M., Pan, L., Liu, Z., Ding, B., and Li, Y. (2025). Microremed: Benchmarking llms in microservices remediation.
Zheng, L., Chen, Z., He, J., and Chen, H. (2024). Mulan: Multi-modal causal structure learning and root cause analysis for microservice systems. In Proceedings of the ACM Web Conference 2024, WWW ’24, page 4107–4116, New York, NY, USA. Association for Computing Machinery.
Zota, R. D., Bărbulescu, C., and Constantinescu, R. (2025). A practical approach to defining a framework for developing an agentic AIOps system. Electronics (Basel), 14(9):1775.
Publicado
19/07/2026
Como Citar
SOUZA, Reinan Gabriel Dos Santos; COLAÇO JÚNIOR, Methanias.
Cloud Microservices: An Empirical Study of MCP-Orchestrated LLM Agents for Incident Triage. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 53. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 191-202.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2026.21828.
