What is required to run DICOM MCP Server?
UV must be installed and available in your system PATH. You can install it with `pip install uv`.
@MCP-Mirror
基本情報
Mirror of
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": {
"fluxinc_dicom-mcp-server": {
"command": "uv",
"args": [
"pip",
"install",
"mcp[cli]"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
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。
DICOM MCP Server is a Model Context Protocol (MCP) server for DICOM connectivity testing. It allows MCP clients—such as Claude—to perform DICOM operations like C-ECHO by querying configured DICOM nodes. It is intended for developers and administrators who need to verify DICOM connectivity from within an MCP environment.
Install UV, then install dependencies with uv pip install mcp[cli]. Optionally register the server with Claude via mcp install server.py. Run directly with uv run server.py (starts on 0.0.0.0:8080). Configure DICOM nodes in a nodes.yaml file. Use tools such as list_dicom_nodes(), dicom_cecho_by_name(), and dicom_cecho() through the MCP interface.
UV must be installed and available in your system PATH. You can install it with `pip install uv`.
Create a `nodes.yaml` file with entries for each node, specifying AE title, IP address, and port. You can also define local AE titles to use for C-ECHO operations.
The server provides C-ECHO operations, both by node name (using the configuration) and with explicit parameters. It also offers a tool to list all configured nodes.
Run `mcp install server.py` after installing dependencies. This registers the server so Claude can automatically manage it.
This error typically means UV is not installed or not in your system PATH, or the Python executable is not accessible to the MCP client. Ensure UV is properly installed and visible, and try using an explicit path to UV.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Hindsight: Agent Memory That Learns
🚀 The fast, Pythonic way to build MCP servers and clients.
Open-source MCP to use Blender with any LLM

Model Context Protocol Servers
コメント