dicom-mcp MCP Server

What does “dicom-mcp” MCP Server do?

The dicom-mcp MCP Server is a specialized Model Context Protocol (MCP) server designed for seamless interaction with DICOM servers, including PACS (Picture Archiving and Communication Systems) and VNA (Vendor Neutral Archives). It empowers AI assistants to perform complex operations on medical imaging data, such as querying patient records, reading clinical reports, and moving imaging series between systems. By exposing these core DICOM and PACS operations as standardized, tool-like endpoints, dicom-mcp enables automation and intelligent workflows for medical imaging, supporting tasks like database queries, report extraction, and integration with external AI diagnostic endpoints. This greatly enhances developer productivity and enables advanced healthcare applications that require secure, programmatic access to medical imaging archives.

List of Prompts

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

List of Tools

• query_patients: Search for patients on the DICOM server using various criteria.
• query_studies: Retrieve study metadata for specified patients or based on filters.
• query_series: List imaging series within a study or matching filters.
• extract_pdf_text_from_dicom: Extract and return the text from encapsulated PDF reports within DICOM instances.
• move_series: Send a DICOM series to a specified destination (e.g., an AI endpoint for further analysis).

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Patient and Study Querying: Enables developers to search and retrieve metadata for patients, studies, and imaging series, supporting medical record review and cohort selection.
• Clinical Report Extraction: Automates retrieval and parsing of clinical reports stored as PDF within DICOM studies, making it easier to summarize and analyze historical findings.
• AI Workflow Integration: Facilitates sending of imaging data to AI endpoints for processing tasks like segmentation or diagnosis, streamlining advanced imaging pipelines.
• Imaging Data Movement: Automates the transfer of DICOM series between systems or destinations, supporting multi-site collaborations or research.
• Connection Management: Provides utilities to manage and understand available query options and DICOM server capabilities, aiding system integration.

How to set it up

Windsurf

1. Ensure Python 3.12+ is installed.
2. Locate your Windsurf configuration file.
3. Add the dicom-mcp MCP server using the following JSON snippet:

   {
     "mcpServers": {
       "dicom-mcp": {
         "command": "dicom-mcp",
         "args": []
       }
     }
   }
   

4. Save the file and restart Windsurf.
5. Verify the server is running by checking the Windsurf MCP panel.

Claude

1. Install Python 3.12+.
2. Locate the Claude configuration file.
3. Add the dicom-mcp MCP server:

   {
     "mcpServers": {
       "dicom-mcp": {
         "command": "dicom-mcp",
         "args": []
       }
     }
   }
   

4. Save changes and restart Claude.
5. Confirm integration via the Claude UI.

Cursor

1. Make sure Python 3.12+ is available.
2. Open Cursor’s settings/configuration panel.
3. Insert the following under MCP servers:

   {
     "mcpServers": {
       "dicom-mcp": {
         "command": "dicom-mcp",
         "args": []
       }
     }
   }
   

4. Save and restart Cursor.
5. Check that dicom-mcp appears in MCP server listings.

Cline

1. Confirm Python 3.12+ is installed.
2. Edit your Cline configuration file.
3. Add dicom-mcp MCP server details:

   {
     "mcpServers": {
       "dicom-mcp": {
         "command": "dicom-mcp",
         "args": []
       }
     }
   }
   

4. Save and restart Cline.
5. Verify the dicom-mcp server is accessible from Cline.

Securing API Keys Using Environment Variables

For systems requiring API keys or credentials, use environment variables for secure injection. Example:

{
  "mcpServers": {
    "dicom-mcp": {
      "command": "dicom-mcp",
      "args": [],
      "env": {
        "DICOM_USERNAME": "${DICOM_USERNAME}",
        "DICOM_PASSWORD": "${DICOM_PASSWORD}"
      },
      "inputs": {
        "server_url": "https://your.dicom.server/api"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "dicom-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “dicom-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the above two tables, dicom-mcp provides excellent documentation on its core tools and setup but lacks explicit prompt templates and resource definitions. Sampling and Roots support are not mentioned. The project is mature and has a clear license, but some MCP features are not fully exposed.

MCP Score

Overall rating: 7/10
dicom-mcp is robust and well-documented for DICOM/PACS integration, but would benefit from explicit prompts/resources and clearer mention of advanced MCP features.