DICOM-MCP
# 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
## 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`
<details>
<summary>Development/Unpublished Servers Configuration</summary>
```
"mcpServers": {
"DICOM-MCP": {
"command": "uv",
"args": [
"--directory",
"/Users/shaunporwal/Documents/GitHub/projects/DICOM-MCP",
"run",
"DICOM-MCP"
]
}
}
```
</details>
<details>
<summary>Published Servers Configuration</summary>
```
"mcpServers": {
"DICOM-MCP": {
"command": "uvx",
"args": [
"DICOM-MCP"
]
}
}
```
</details>
## Development
### Building and Publishing
To prepare the package for distribution:
1. Sync dependencies and update lockfile:
```bash
uv sync
```
2. Build package distributions:
```bash
uv build
```
This will create source and wheel distributions in the `dist/` directory.
3. Publish to PyPI:
```bash
uv publish
```
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token: `--token` or `UV_PUBLISH_TOKEN`
- Or username/password: `--username`/`UV_PUBLISH_USERNAME` and `--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](https://github.com/modelcontextprotocol/inspector).
You can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command:
```bash
npx @modelcontextprotocol/inspector uv --directory /Users/shaunporwal/Documents/GitHub/projects/DICOM-MCP run dicom-mcp
```
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.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.