Dicom
Enables Large Language Models to access and analyze medical imaging metadata from DICOM servers.
About
dicom-mcp is a Model Context Protocol (MCP) server designed to facilitate interactions with DICOM (Digital Imaging and Communications in Medicine) servers. It provides a suite of tools that allows AI assistants and Large Language Models to seamlessly query and analyze medical imaging metadata. The server supports standard DICOM networking protocols for retrieving patient information, studies, series, and instances. Additionally, it can extract text from encapsulated PDF documents stored within DICOM format, making clinical reports accessible for analysis. Built on pynetdicom and adhering to the Model Context Protocol specification, dicom-mcp serves as a bridge between medical imaging data and advanced AI analysis.
Key Features
- Queries DICOM servers for patient, study, series, and instance data.
- Supports multiple DICOM nodes and calling AE titles via configuration.
- Retrieves DICOM instances and saves them to the local filesystem.
- Extracts text from DICOM encapsulated PDFs.
- Provides customizable attribute presets for queries.
Use Cases
- Extracting clinical information from PDF reports stored in DICOM format.
- Enabling AI assistants to access and analyze medical imaging metadata.
- Building AI-powered diagnostic tools using medical imaging data.