DICOM-MCP
The DICOM-MCP server is a versatile tool that provides two main functionalities:
Note Management
Add new notes with name and content
Access stored notes via custom
note://URI schemeSummarize all stored notes (with optional style)
DICOM File Processing
Scan directories for DICOM files and organize them into series
Extract detailed metadata from DICOM files
Load DICOM series into memory by UID
Load and associate DICOM SEG files with reference images
Crop loaded DICOM images by removing boundary percentage
Allows publishing the MCP server package to PyPI for distribution to other users
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DICOM-MCP add a note named 'CT scan findings' with the content 'Patient shows no acute abnormalities'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DICOM-MCP MCP server
MCP to work with DICOM images
Components
Resources
The server implements a simple note storage system with:
Custom note:// URI scheme for accessing individual notes
Each note resource has a name, description and text/plain mimetype
Prompts
The server provides a single prompt:
summarize-notes: Creates summaries of all stored notes
Optional "style" argument to control detail level (brief/detailed)
Generates prompt combining all current notes with style preference
Tools
The server implements one tool:
add-note: Adds a new note to the server
Takes "name" and "content" as required string arguments
Updates server state and notifies clients of resource changes
Related MCP server: TriliumNext Notes' MCP Server
Configuration
[TODO: Add configuration details specific to your implementation]
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development
Building and Publishing
To prepare the package for distribution:
Sync dependencies and update lockfile:
uv syncBuild package distributions:
uv buildThis will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
uv publishNote: You'll need to set PyPI credentials via environment variables or command flags:
Token:
--tokenorUV_PUBLISH_TOKENOr username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/shaunporwal/Documents/GitHub/projects/DICOM-MCP run dicom-mcpUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Available Tools
6 toolsadd-noteC
Add a new note
Inputs: name (required), content (required).
crop-dicom-imageB
Crop a loaded DICOM image by removing boundary percentage
Inputs: series_uid (required), boundary_percentage.
extract-dicom-metadataC
Extract detailed metadata from a DICOM file
Inputs: dicom_file (required).
load-dicom-segC
Load a DICOM SEG file and associate it with a reference image
Inputs: seg_file (required), reference_series_uid.
load-dicom-seriesC
Load a DICOM series into memory for processing
Inputs: series_uid (required).
scan-dicom-directoryB
Scan a directory for DICOM files and organize them into series
Inputs: directory (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: adding notes, cropping images, extracting metadata, loading segmentation files, loading series, and scanning directories. There is no overlap in functionality, making it easy for an agent to select the right tool for each task.
The tools follow a consistent verb-noun pattern with hyphens (e.g., add-note, crop-dicom-image), except for 'scan-dicom-directory' which uses 'scan' instead of 'load' or similar, but this minor deviation doesn't break overall readability. The naming is predictable and easy to understand.
With 6 tools, this server is well-scoped for DICOM processing, covering key operations like loading, scanning, extracting metadata, cropping, and adding notes. Each tool earns its place without feeling too sparse or bloated, fitting typical use cases in this domain.
The toolset covers core DICOM workflows including loading, scanning, metadata extraction, and basic image manipulation. Minor gaps exist, such as the lack of tools for saving or exporting processed DICOM files, but agents can likely work around this with the provided operations.
Maintenance
Related MCP Connectors
Model Context Protocol server for Studex tools, notifications, and profile integrations
Model Context Protocol server for todo.vu task management and time tracking.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Google Keep-style notes app with an MCP server for AI agents to read/write notes.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA connectivity testing server that enables DICOM network operations (like C-ECHO) through Claude's Model Context Protocol, with support for node configuration management.3GNU Lesser General Public v2.1 only
- FlicenseAqualityCmaintenanceA model context protocol server that allows interaction with TriliumNext Notes, providing tools to create, search, retrieve, update, and delete notes through natural language commands.969-
- FlicenseCqualityDmaintenanceA Model Context Protocol server that implements a simple notes system, allowing users to create, list, and summarize text notes.3-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server for managing text notes, with resources (note:// URIs), tools (create_note), and prompts (summarize_notes).-