DICOM MCP Server for Medical Imaging Systems 🏥
@ChristianHinge
DICOM MCP Server for Medical Imaging Systems 🏥 について
Model Context Protocol (MCP) for interacting with dicom servers (PACS etc.)
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"dicom-mcp": {
"command": "uv",
"args": [
"tool",
"install",
"dicom-mcp"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is DICOM MCP Server?
The DICOM MCP Server enables AI assistants to query, read, and send data on DICOM servers such as PACS and VNA. It provides tools for metadata exploration, PDF report extraction, and DICOM image movement, designed for medical imaging workflows.
How to use DICOM MCP Server?
Install via uv tool install dicom-mcp. Create a YAML configuration file defining DICOM nodes and the calling AE title. Add the server to your MCP client configuration (e.g., claude_desktop_config.json) using uvx dicom-mcp /path/to/your_config.yaml. Tools are invoked by the AI assistant after configuration.
Key features of DICOM MCP Server
- Query patients, studies, series, and instances by multiple criteria.
- Extract text from encapsulated PDFs within DICOM instances.
- Send series or studies to other DICOM nodes using C-MOVE.
- List, switch, and verify connectivity to configured DICOM nodes.
- Choose metadata detail levels (minimal, standard, extended).
Use cases of DICOM MCP Server
- An AI assistant queries a patient’s studies and extracts a PDF report to summarize findings.
- A CT series is moved to a segmentation node for volume calculation and results retrieval.
- Chain query and move tools to compare past and current radiological measurements.
FAQ from DICOM MCP Server
What libraries does DICOM MCP Server build on?
It uses pynetdicom for DICOM networking and PyPDF2 for PDF text extraction.
Is DICOM MCP Server safe for clinical use?
No. It is not meant for clinical use and should not be connected to live hospital databases or systems with patient-sensitive data due to risk of data loss or leakage.
What are the runtime requirements?
Python 3.12+ and a running DICOM server (a sample Orthanc server is provided via Docker for testing).
Where does data live?
Data remains on the DICOM server; the server only queries, reads, and moves data on that server.
Which transport and authentication does it support?
Transport is over stdio (via MCP protocol). Authentication is handled by the DICOM AE title and node configuration defined in the YAML file.
「その他」の他のコンテンツ
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Awesome Mlops
visengerA curated list of references for MLOps
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
コメント