MediFlow: MCP-Based Healthcare Workflow Orchestration System

Author

Shivakumara Naik, Veeresh Devadhar, Prajwal Horatti , Vishnu K V, Sumana C

Abstract

Healthcare institutions manage various activities such as patient registration, appointment scheduling and medical-record management. Performing these activities manually can cause delays, errors and difficulties in coordination.This paper presents MediFlow, an MCP-based healthcare workflow orchestration system that uses Artificial Intelligence, Large Language Models (LLMs) and multi-agent systems to automate administrative healthcare processes. The system consists of specialized agents for patient registration, appointment scheduling, medical-record management and data validation. Model Context Protocol (MCP) enables communication between AI agents and external tools.The system uses React for the frontend, Python and FastAPI for backend operations, Supabase for database management and Redis for shared workflow context. A centralized dashboard helps monitor patient information, appointments and workflow status. MediFlow aims to improve administrative efficiency and coordination while supporting healthcare professionals in routine operations..

Keywords

MCP, Artificial Intelligence, Multi-Agent Systems, Healthcare Automation, LLM, FastAPI, Digital Healthcare.

Full Text:

Download Paper PDF

References

Research Papers:

[1] S. Tripathi, R. Sukumaran, and T. S. Cook, “Efficient Healthcare with Large Language Models: Optimizing Clinical Workflow and Enhancing Patient Care,” Journal of the American Medical Informatics Association, vol. 31, no. 6, pp. 1436–1440, 2024. DOI: 10.1093/jamia/ocad258.

[2] J. Qiu et al., “LLM-Based Agentic Systems in Medicine and Healthcare,” Nature Machine Intelligence, vol. 6, pp. 1418–1420, 2024. DOI: 10.1038/s42256-024-00944-1.

[3] D. Wang and S. Zhang, “Large Language Models in Medical and Healthcare Fields: Applications, Advances, and Challenges,” Artificial Intelligence Review, vol. 57, article 299, 2024. DOI: 10.1007/s10462-024-10921-0.

[4] H. G. Pandey, A. Amod, and S. Kumar, “Advancing Healthcare Automation: Multi-Agent System for Medical Necessity Justification,” Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pp. 39–49, 2024. DOI: 10.18653/v1/2024.bionlp-1.4.

[5] L. Wang et al., “A Survey on Large Language Model Based Autonomous Agents,” Frontiers of Computer Science, vol. 18, article 186345, 2024. DOI: 10.1007/s11704-024-40231-1.

[6] N. Mehandru et al., “Evaluating Large Language Models as Agents in the Clinic,” npj Digital Medicine, vol. 7, article 84, 2024.

[7] Z. Al Nazi and W. Peng, “Large Language Models in Healthcare and Medical Domain: A Review,” Informatics, vol. 11, no. 3, article 57, 2024. DOI: 10.3390/informatics11030057.

[8] V. Ayyagari, “Model Context Protocol for Agentic AI: Enabling Contextual Interoperability Across Systems,” International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 3, pp. 6072–6082, 2025. DOI: 10.22399/ijcesen.3678.

Share your valuable work from Social Media Buttons