MCP-MedImg: Enabling Standardized PACS-AI Integration through the Model Context Protocol

Reference implementation for the paper:
"MCP-MedImg: Enabling Standardized PACS-AI Integration through the Model Context Protocol"

Author: Xiong Shi (ORCID: 0009-0006-2745-491X)

Architecture

MCP-MedImg extends the Model Context Protocol (MCP) with a four-layer protocol stack specifically designed for medical imaging workflows:

• L1 Transport: DICOMweb / DICOM C-MOVE / dicom-mcp compatibility wrapper

• L2 Security & Compliance: Hierarchical PHI de-identification + 14-column cryptographic audit trail

• L3 AI Orchestration: Model registry, inspection-type routing, version management, result formatting

• L4 Application Semantics: Lesion encoding (RADS/BI-RADS), conditional verification state machine

Related MCP server: Smart EHR MCP Server

Quick Start

Prerequisites

• Ubuntu 22.04 (recommended) / macOS / Windows WSL2

• Python 3.10+

• Docker & Docker Compose

• NVIDIA GPU with CUDA 12.1+ (optional; Mock engine available for CPU-only environments)

1. Clone & Install

git clone https://github.com/Xiong-Shi/MCP-MedImg.git
cd MCP-MedImg
pip install -r requirements.txt

2. Start Orthanc PACS

docker-compose -f config/orthanc/docker-compose.yml up -d

3. Run Unit Tests (Protocol Validation)

pytest tests/ -v --tb=short
# Expected: 132 passing, 3 skipped across 10 validation scenarios

4. Run Benchmarks

bash scripts/reproduce_lidc_benchmark.sh      # Table 18: LIDC-IDRI inference latency (n=200)
bash scripts/reproduce_heart_benchmark.sh     # Table 19, 22: MSD Heart 5-fold validation
bash scripts/reproduce_protocol_overhead.sh   # Table 20, 21: Protocol overhead decomposition (n=98)

Datasets & Model Weights

Due to file size limits, pretrained model weights and full preprocessed datasets are available via separate download:

Download instructions:

bash scripts/download_pretrained_weights.sh

Key Experimental Results

Analysis Figures: Detailed analysis charts (LIDC bimodal distribution, PROTO error robustness) are available in the Zenodo dataset:

This implementation addresses the MCP-38 threat taxonomy for medical imaging:

• Hierarchical PHI de-identification (Patient / Department / System level)

• Cryptographic audit trails with SHA-256 hashing

• Containerized sandbox execution

• Input sanitization against indirect prompt injection

Reproducibility

All experimental results from the paper can be reproduced via the scripts in scripts/.

Citation

If you use this code, please cite:

@article{mcp_medimg_2026,
  title={MCP-MedImg: Enabling Standardized PACS-AI Integration through the Model Context Protocol},
  author={[Author Names]},
  journal={[Journal Name]},
  year={2026}
}

License

This project is licensed under the Apache License 2.0 - see LICENSE file.

Disclaimer

This is a research prototype for protocol validation and reproducibility. Not for clinical use without appropriate regulatory approval (FDA/NMPA/CE).