Coding-Free and Privacy-Preserving MCP Framework for Clinical Agentic Research Intelligence System
Summary: arXiv:2604.12258v1 Announce Type: cross
Abstract: Clinical research involves labor-intensive processes such as study design, cohort construction, model development, and documentation, requiring domain expertise, programming skills, and access to sensitive patient data. These demands create barriers for clinicians and external researchers conducting data-driven studies. To overcome these limitations, we developed a Clinical Agentic Research Intelligence System (CARIS) that automates the clinical research workflow while preserving data privacy, enabling comprehensive studies without direct access to raw data.
CARIS integrates Large Language Models (LLMs) with modular tools via the Model Context Protocol (MCP), enabling natural language-driven orchestration of appropriate tools. Databases remain securely within the MCP server, and users access only the outputs and final research reports. Based on user intent, CARIS automatically executes the full pipeline:
- Research planning
- Literature search
- Cohort construction
- Institutional Review Board (IRB) documentation
- Vibe Machine Learning (ML)
- Report generation
The system incorporates iterative human-in-the-loop refinement to ensure accuracy and relevance. We evaluated CARIS on three heterogeneous datasets with distinct clinical tasks. Research plans and IRB documents were finalized within three to four iterations, using evidence from literature and data. The system supported Vibe ML by exploring feature-model combinations, ranking the top ten models, and generating performance visualizations.
Final reports showed high completeness based on a checklist derived from the TRIPOD+AI framework, achieving 96% coverage in LLM evaluation and 82% in human evaluation. CARIS demonstrates that agentic AI can transform clinical hypotheses into executable research workflows across heterogeneous datasets. By eliminating the need for coding and direct data access, the system lowers barriers and bridges public and private clinical data environments.
Key Features of CARIS
- Automation: Streamlines the clinical research process, reducing the workload for researchers.
- Data Privacy: Protects sensitive patient information by keeping databases secure within the MCP server.
- User-Friendly: Allows clinicians with minimal programming skills to conduct data-driven research through natural language commands.
- Iterative Refinement: Enhances the quality of research through feedback loops involving human oversight.
- High Completeness: Reports generated are comprehensive and adhere to established frameworks, ensuring rigorous standards.
Conclusion
The Clinical Agentic Research Intelligence System represents a significant advancement in the field of clinical research. By leveraging the capabilities of large language models and modular tools, CARIS democratizes access to research capabilities while maintaining the highest standards of data privacy. This innovative approach not only enhances research efficiency but also fosters collaboration between public and private sectors in clinical data utilization.