dicom-mcp
The DICOM MCP Server is designed to facilitate AI assistants in interacting with medical imaging DICOM servers. It provides tools for querying patient data, reading reports, and sending images to AI endpoints, enhancing the capabilities of large language models in the medical imaging domain.
Is DICOM-MCP suitable for clinical use?
No, DICOM-MCP is not intended for clinical use and should not be connected with live hospital databases.
What are the prerequisites for running tests?
Tests require a running Orthanc DICOM server, which can be set up using Docker.
How can I debug server communication?
Use the MCP Inspector for debugging by running npx @modelcontextprotocol/inspector uv run dicom-mcp /path/to/your_config.yaml --transport stdio.
What tools are available for querying metadata?
Tools like query_patients, query_studies, and query_series are available for querying metadata.
How can I send DICOM images to another node?
Use the move_series or move_study tools to send DICOM images to another configured DICOM node.