An MCP server that enables AI assistants to query, read, and transfer data on DICOM servers (PACS, VNA, etc.) for medical imaging systems, including text extraction from DICOM-encapsulated PDF reports.

Installation

Installation via UV Tool

uv tool install dicom-mcp

From Source Code

git clone https://github.com/ChristianHinge/dicom-mcp
cd dicom mcp
uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"

Configuration

Claude Desktop

{
  "mcpServers": {
    "dicom": {
      "command": "uv",
      "args": ["tool","dicom-mcp", "/path/to/your_config.yaml"]
    }
  }
}

Development

{
    "mcpServers": {
        "arxiv-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/cloned/dicom-mcp",
                "run",
                "dicom-mcp",
                "/path/to/your_config.yaml"
            ]
        }
    }
}

Available Tools

Tool	Description
query_patients	Search for patients by criteria such as name, ID, or date of birth
query_studies	Search for studies by patient ID, date, modality, description, accession number, or Study UID
query_series	Search for series within a specific study by modality, series number/description, or Series UID
query_instances	Search for individual instances (images/objects) in a series by instance number or SOP Instance UID
extract_pdf_text_from_dicom	Retrieve a specific DICOM instance with encapsulated PDF and extract its text content
move_series	Send a specific DICOM series to another configured DICOM node via C-MOVE
move_study	Send an entire DICOM study to another configured DICOM node via C-MOVE
list_dicom_nodes	Display the current active DICOM node and list all configured nodes
switch_dicom_node	Switch the active DICOM node for subsequent operations
verify_connection	Test DICOM network connectivity with the current active node via C-ECHO
get_attribute_presets	List available detail levels (minimal, standard, extended) for metadata query results

Capabilities

• Metadata Querying: Search for patients, studies, series, and instances using various criteria
• DICOM Report Reading (PDF): Retrieve DICOM instances with encapsulated PDFs and extract text content
• DICOM Image Transfer: Send series or studies to other DICOM destinations for AI processing
• Connection Management and Query Option Understanding: Use utility tools to manage connections and understand query options

Usage Examples

Any significant findings in John Doe's previous CT report?

What's the volume of his spleen at the last scan and the scan today?

Notes

Requires a YAML configuration file defining DICOM nodes and calling AE titles. WARNING: Not intended for clinical use and should not be connected to active hospital databases or databases containing confidential patient data.