Pemanfaatan Model Context Protocol untuk Otomatisasi Root Cause Analysis pada Microservices Berbasis Docker
- Muhammad Silmy Firdaus Universitas Gadjah Mada, Daerah Istimewa Yogyakarta, Indonesia
-
Sahirul Alam
*
Universitas Gadjah Mada, Daerah Istimewa Yogyakarta,
Indonesia
(*) Corresponding Author
Abstract
Microservices architecture deployed in Docker container environments offers high scalability, yet generates large and segmented telemetry data that prevents conventional monitoring methods from supporting rapid root cause analysis. Administrators must manually trace hundreds of metrics and logs through complex dashboards, while existing chatbot approaches remain rule-based and limited to presenting raw data without deep analysis. This study designs and implements a monitoring system that integrates a Large Language Model (LLM) through the Model Context Protocol (MCP) to automate disruption analysis on Docker-based microservices. A custom MCP Server was developed by modifying the open-source Prometheus-MCP-Server repository to bridge two telemetry sources: container metrics collected by Prometheus via cAdvisor, and container logs retrieved from the Docker Daemon via the Docker SDK, combined with a natural-language interface provided by the LLM through Cursor as the MCP Client. The research object consisted of eight e-commerce microservice containers running on a Virtual Private Server. Telemetry accuracy validation yielded a mean MAE of 0.1071 MB and a mean MAPE of 0.29% across all containers. Response-time testing showed the system responding within 3-23 seconds, with the LLM reasoning component dominating 98.72%-99.81% of total response time, while the MCP Server contributed only 0.044 seconds of overhead. Scalability testing with 1-10 concurrent users showed elastic CPU usage and stable RAM consumption within 165.7-169.3 MB. These findings demonstrate the technical feasibility of MCP-based LLM integration for supporting microservices incident analysis through unified access to container metrics and logs, while highlighting limitations in RCA diagnostic accuracy evaluation and production-scale scalability testing.
Downloads
References
Al-Safi, H., Ibrahim, H., & Steenson, P. (2025). Vega: LLM-driven intelligent chatbot platform for Internet of Things control and development. Sensors, 25(12), 3809. https://doi.org/10.3390/s25123809
Anam, K., & Subardono, A. (2021). Implementasi sistem monitoring resource Server berbasis Prometheus dan Grafana dengan notifikasi Telegram [Tugas Akhir, Universitas Gadjah Mada]. https://etd.repository.ugm.ac.id/penelitian/detail/204580
Blinowski, G., Ojdowska, A., & Przybylek, A. (2022). Monolithic vs. microservice architecture: A performance and scalability evaluation. IEEE Access, 10, 20357–20374. https://doi.org/10.1109/ACCESS.2022.3152803
Espinosa-Luna, B. H., Castillo-Oliva, J., Garcia-Gutierrez, W. F., & Mendoza-de-los-Santos, A. C. (2025). Systems monitoring platform integrating artificial intelligence for incident response in Servers. Revista Cientifica de Sistemas e Informatica, 5(2), e811. https://doi.org/10.51252/rcsi.v5i2.811
Gupta, P., Jain, P., Chauhan, V. K., Kumari, S., & Mall, R. (2026). Multimodal root cause analysis for cloud microservices: Integrating temporal convolutional networks with causal discovery and LLM priors. TechRxiv. https://doi.org/10.36227/techrxiv.177126526.67932591/v1
Hodson, T. O. (2022). Root-mean-square error (RMSE) or Mean Absolute Error (MAE): When to use them or not. Geoscientific Model Development, 15(14), 5481–5487. https://doi.org/10.5194/gmd-15-5481-2022
Hou, X., Zhao, Y., Wang, S., & Wang, H. (2025). Model Context Protocol (MCP): Landscape, security threats, and future research directions. arXiv. https://doi.org/10.48550/arXiv.2503.23278
Ishlakhuddin, F., & Sn, A. (2021). Ontology-based chatbot to support monitoring of Server performance and security by rule-base. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 15(2), 131. https://doi.org/10.22146/ijccs.58588
Lee, C., Yang, T., Chen, Z., Su, Y., & Lyu, M. R. (2023). Eadro: An end-to-end troubleshooting framework for microservices on multi-source data. arXiv. https://doi.org/10.48550/ARXIV.2302.05092
Mohammed, A., & Kora, R. (2025). A comprehensive overview and analysis of large language models: Trends and challenges. IEEE Access, 13, 95851–95875. https://doi.org/10.1109/ACCESS.2025.3573955
Pedroso, D. F., Almeida, L., Pulcinelli, L. E. G., Aisawa, W. A. A., Dutra, I., & Bruschi, S. M. (2025). Anomaly detection and root cause analysis in cloud-native environments using large language models and Bayesian networks. IEEE Access, 13, 77550–77564. https://doi.org/10.1109/ACCESS.2025.3565220
Robeson, S. M., & Willmott, C. J. (2023). Decomposition of the Mean Absolute Error (MAE) into systematic and unsystematic components. PLOS ONE, 18(2), e0279774. https://doi.org/10.1371/journal.pone.0279774
Rohmawati, L., Nugroho, M. A., & Wagito, W. (2023). Implementasi chatbot pada WhatsApp untuk monitoring sumber daya Server. Journal of Information System Management (JOISM), 4(2), 107–112. https://doi.org/10.24076/joism.2023v4i2.960
Sahimin, Hariyadi, P., & Marzuki, K. (2025). Penerapan Prometheus terintegrasi Grafana untuk monitoring virtualisasi berbasis Proxmox Virtual Environment.
Saory, F., Jaman, J. H., & Author, C. (2025). Sistem monitoring Server menggunakan Prometheus dan Grafana dengan integrasi Slack di PT. Atlas Lintas Indonesia. Jurnal Informatika dan Teknik Elektro Terapan, 13(3S1). https://doi.org/10.23960/jitet.v13i3S1.8024
Saputra, M. Y. E., Noprianto, Arief, S. N., Wijayaningrum, V. N., & Syaifudin, Y. W. (2024). Real-time Server monitoring and notification system with Prometheus, Grafana, and Telegram integration. In 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) (pp. 1808–1813). IEEE. https://doi.org/10.1109/ICETSIS61505.2024.10459488
Scheinert, D., et al. (2026). Beyond microservices: Testing web-scale RCA methods on GPU-driven LLM workloads. arXiv. https://doi.org/10.48550/arXiv.2603.02057
Sekar, S. P. (2025). AI-driven cloud-native observability: Leveraging LLMs for application modernization in a platform as a service model. World Journal of Advanced Research and Reviews, 26(2), 347–358. https://doi.org/10.30574/wjarr.2025.26.2.1621
Soldani, J., & Brogi, A. (2021). Anomaly detection and failure root cause analysis in (micro)service-based cloud applications: A survey. arXiv. https://doi.org/10.48550/ARXIV.2105.12378
Zhou, L., Liu, A., Liu, H., He, M., & Zhang, H. (2026). Root cause analysis method based on large language models with residual connection structures. arXiv. https://doi.org/10.48550/ARXIV.2602.08804
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Pemanfaatan Model Context Protocol untuk Otomatisasi Root Cause Analysis pada Microservices Berbasis Docker
Copyright (c) 2026 Muhammad Silmy Firdaus, Sahirul Alam
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
