DICOM MCP Server

@fluxinc

Repository

Basic information

About DICOM MCP Server

A server for managing contextual data in DICOM tools, supporting medical imaging and machine learning workflows.

#dicom #mcp #server#medical-imaging#machine-learning

DICOM MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dicom-mcp-server": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "mcp[cli]"
      ]
    }
  }
}

DICOM MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is DICOM MCP Server?

A Model Context Protocol (MCP) server for DICOM connectivity testing. It allows performing C‑ECHO operations either by referencing configured DICOM nodes from a YAML file or by specifying remote AE title, IP, and port directly.

How to use DICOM MCP Server?

Install uv and then run uv pip install mcp[cli] for a traditional setup, or mcp install server.py to register the server with Claude. Start the server with uv run server.py (defaults to 0.0.0.0:8080). Configuration is managed through a nodes.yaml file that stores DICOM node definitions and local AE titles.

Key features of DICOM MCP Server

DICOM C‑ECHO operations via node names or explicit parameters
Configuration stored in a YAML file (nodes.yaml)
Two installation methods: traditional or MCP‑install for Claude
Multiple local AE titles can be defined and selected per operation
Listing all configured DICOM nodes from the YAML file

Use cases of DICOM MCP Server

Verify DICOM connectivity between a local application and a remote PACS
Perform C‑ECHO tests against multiple PACS nodes without re‑entering AE titles, IPs, and ports
Integrate DICOM network checks into Claude‑powered workflows via the MCP interface

Frequently asked questions

What are the prerequisites for the DICOM MCP Server?

You must install `uv` (pip install uv) and ensure it is available in your system’s PATH.

How do I install the server for use with Claude?

Run `mcp install server.py` to register the server with Claude. Claude will then manage the server automatically.

What is the `nodes.yaml` file for?

It stores DICOM node configurations (AE title, IP, port, description) and local AE titles, allowing you to reference nodes by name in C‑ECHO operations.

How do I fix a "spawn uv ENOENT" error?

Ensure `uv` is installed and in your PATH (`which uv`), use an accessible Python environment, or run the server with an explicit path to `uv`.

What DICOM tools are provided?

The server offers three tools: `list_dicom_nodes()` to list configured nodes, `dicom_cecho_by_name()` to echo a named node, and `dicom_cecho()` for direct C‑ECHO with explicit parameters.

Comments

More Other MCP servers

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3