DICOMweb MCP Server
Summary: An MCP server that exposes a DICOMweb-compliant DICOM archive to AI assistants for natural-language search, inspection, and rendering of medical imaging data.
Search studies (
find-studies) by patient name, date range, modality, or any DICOM attribute — sorted newest firstBrowse series (
find-series) within a study, sorted by series dateList instances (
find-instances) within a series, sorted by instance numberFind Structured Reports (
find-structured-reports) by filtering SR-modality series and SR SOP Class UIDsFind Encapsulated PDF reports (
find-encapsulated-pdf-reports) via DOC-modality series and the EP SOP Class UIDRead SR text (
get-structured-report-text) — converts an SR instance to human-readable textExtract PDF text (
get-encapsulated-pdf-report-text) — works only for text-based PDFs; no OCR for scanned imagesInspect metadata (
get-instance-metadata) — formats all DICOM attributes of an instance as text, without pixel dataRender frames (
render-instance-frame) — returns a chosen frame as an inline JPEG or PNG imageFlexible querying — space-separated
key=valuefilters using DICOM keyword names or 8-digit hex tags, with wildcards,fuzzymatching,limit,offset, andincludefield=allWorks with any MCP client (Claude Desktop, VS Code Copilot, Cursor) against a DICOMweb server supporting QIDO-RS and WADO-RS, with optional basic/bearer auth and configurable timeouts
dicomweb-mcp-server
A Model Context Protocol (MCP) server that exposes a DICOMweb-compliant DICOM archive to AI assistants. It lets any MCP-capable client search studies, series and instances, inspect metadata, read Structured and Encapsulated PDF Reports, and render image frames — all through natural language.
Requirements
Node.js 20 or later
A running DICOMweb server supporting QIDO-RS and WADO-RS (e.g. orthanc)
The following endpoints must be supported by the DICOMweb server:
Endpoint | Service | Used by |
| QIDO-RS | Search studies |
| QIDO-RS | Search series |
| QIDO-RS | Search instances, search structured reports, search encapsulated PDF reports |
| WADO-RS | Get instance metadata, get structured report text, get encapsulated PDF report text |
| WADO-RS | Render instance frame |
Related MCP server: DICOM MCP Server
Installation
Using npx (recommended — no local install needed)
npx dicomweb-mcp-serverThe server reads its configuration from a .env file located in the same directory as the script (see Configuration below).
Global install
npm install -g dicomweb-mcp-server
dicomweb-mcp-serverConfiguration
Create a .env file with the connection details for your DICOMweb server. Place the file next to wherever the server is executed from (or in the working directory you configure in your MCP client).
# Required
DICOMWEB_HOST=https://your-dicomweb-server/dicomweb
# Optional — authentication
DICOMWEB_AUTH=basic # basic | bearer
DICOMWEB_USER=username # required when DICOMWEB_AUTH=basic
DICOMWEB_PASS=password # required when DICOMWEB_AUTH=basic
DICOMWEB_TOKEN=your-token # required when DICOMWEB_AUTH=bearer
# Optional — request timeout (milliseconds)
DICOMWEB_TIMEOUT=30000Variable | Required | Description |
| Yes | Base URL of the DICOMweb server (used for both QIDO-RS and WADO-RS requests) |
| No | Authentication type: |
| Conditional | Username — required when |
| Conditional | Password — required when |
| Conditional | Bearer token — required when |
| No | Fetch timeout in milliseconds. Omit to disable. |
MCP Client Setup
Claude Desktop
Add the server to claude_desktop_config.json:
{
"mcpServers": {
"dicomweb": {
"command": "npx",
"args": ["-y", "dicomweb-mcp-server"],
"env": {
"DICOMWEB_HOST": "https://your-dicomweb-server/dicomweb"
}
}
}
}You can supply all environment variables directly in the env block instead of using a .env file.
VS Code (GitHub Copilot Agent Mode)
Add to your VS Code settings.json or workspace .vscode/mcp.json:
{
"servers": {
"dicomweb": {
"type": "stdio",
"command": "npx",
"args": ["-y", "dicomweb-mcp-server"],
"env": {
"DICOMWEB_HOST": "https://your-dicomweb-server/dicomweb"
}
}
}
}Cursor
Add to .cursor/mcp.json in your project root, or to the global ~/.cursor/mcp.json:
{
"mcpServers": {
"dicomweb": {
"command": "npx",
"args": ["-y", "dicomweb-mcp-server"],
"env": {
"DICOMWEB_HOST": "https://your-dicomweb-server/dicomweb"
}
}
}
}Available Tools
find-studies
Searches DICOM studies on the configured DICOMweb server. Results are sorted by study date, newest first.
Parameter | Type | Description |
| string | Space-separated |
Example prompts
"Find all CT studies for patient John Doe"
"Search for studies from January 2024"
find-series
Searches DICOM series within a single study. Results are sorted by series date, newest first.
Parameter | Type | Description |
| string | Study Instance UID — obtain from |
| string | Space-separated |
find-instances
Searches DICOM instances within a single series. Results are sorted by Instance Number ascending.
Parameter | Type | Description |
| string | Study Instance UID — obtain from |
| string | Series Instance UID — obtain from |
| string | Space-separated |
find-encapsulated-pdf-reports
Finds all Encapsulated PDF instances in a study by looking for DOC-modality series and filtering by the Encapsulated PDF SOP Class UID (1.2.840.10008.5.1.4.1.1.104.1).
Parameter | Type | Description |
| string | Study Instance UID — obtain from |
Example prompts
"Find all PDF reports in study 1.2.3.4"
"Are there any encapsulated PDF documents in this study?"
get-encapsulated-pdf-report-text
Retrieves an Encapsulated PDF DICOM instance and extracts its text content.
Parameter | Type | Description |
| string | Study Instance UID |
| string | Series Instance UID |
| string | SOP Instance UID — obtain from |
Note: Text extraction only works for searchable (text-based) PDFs. PDFs that consist entirely of scanned page images without an embedded text layer will yield little or no text. In those cases, no OCR is performed.
Example prompts
"Read the PDF report for SOP instance 1.2.3.4.5"
"What does the encapsulated PDF document say?"
find-structured-reports
Finds all Structured Report (SR) instances in a study by looking for SR-modality series and filtering by known SR SOP Class UIDs.
Parameter | Type | Description |
| string | Study Instance UID — obtain from |
get-structured-report-text
Retrieves a Structured Report instance and converts it to human-readable text.
Parameter | Type | Description |
| string | Study Instance UID |
| string | Series Instance UID |
| string | SOP Instance UID — obtain from |
get-instance-metadata
Retrieves and formats all DICOM attributes of a single instance as human-readable text. Does not retrieve pixel data.
Parameter | Type | Description |
| string | Study Instance UID |
| string | Series Instance UID |
| string | SOP Instance UID — obtain from |
render-instance-frame
Renders a specific frame from a DICOM instance and returns it as an inline image (JPEG or PNG).
Parameter | Type | Description |
| string | Study Instance UID |
| string | Series Instance UID |
| string | SOP Instance UID — obtain from |
| integer | 1-based frame index (use |
| enum |
|
Example prompt
"Show me the first frame of SOP instance 1.2.3.4.5 as a JPEG"
Query Syntax
The query parameter accepted by the search tools is a space-separated list of key=value pairs.
Key formats
Format | Example |
DICOM keyword name |
|
8-digit hex tag |
|
Special keys
Key | Description |
| Maximum number of results to return |
| Skip the first N results (for pagination) |
| Enable fuzzy (phonetic) name matching |
| Request all available DICOM attributes |
Examples
PatientName=DOE*
StudyDate=20240101-20241231 ModalitiesInStudy=CT
00100020=ABC123 limit=10
fuzzymatching=true PatientName=SmithWildcard * is supported in string values where the DICOMweb server allows it.
Typical Workflow
A natural conversational sequence with the MCP server looks like this:
Search studies —
find-studieswith a patient name or date range.Browse series —
find-serieswith the Study Instance UID returned in step 1.List instances —
find-instanceswith Study and Series UIDs from steps 1–2.Inspect or render —
get-instance-metadatafor DICOM attributes, orrender-instance-frameto view pixel data.Read SR reports —
find-structured-reportsthenget-structured-report-textfor SR documents.Read PDF reports —
find-encapsulated-pdf-reportsthenget-encapsulated-pdf-report-textfor Encapsulated PDF documents.
License
dicomweb-mcp-server is released under the MIT License.
Available Tools
9 toolsfind-encapsulated-pdf-reportsA
Finds all Encapsulated PDF DICOM instances in a study by searching for DOC-modality series and filtering by EP SOP Class UIDs. Requires a Study Instance UID from find-studies.
Inputs: studyInstanceUid (required).
find-instancesA
Searches DICOM instances within a single series, sorted by Instance Number ascending. Requires Study and Series Instance UIDs from find-studies and find-series.
Inputs: query (required), studyInstanceUid (required), seriesInstanceUid (required).
find-seriesA
Searches DICOM series within a single study. Returns series sorted by series date, newest first. Does not retrieve instances or image data. Requires a Study Instance UID from find-studies.
Inputs: query (required), studyInstanceUid (required).
find-structured-reportsA
Finds all Structured Report (SR) DICOM instances in a study by searching for SR-modality series and filtering by SR SOP Class UIDs. Requires a Study Instance UID from find-studies.
Inputs: studyInstanceUid (required).
find-studiesA
Searches DICOM studies on the configured DICOMweb server. Returns studies sorted by study date, newest first. Does not retrieve series, instances, or image data.
Inputs: query (required).
get-encapsulated-pdf-report-textA
Retrieves and converts an Encapsulated PDF instance to human-readable text. Requires Study, Series, and SOP Instance UIDs from find-encapsulated-pdf-reports. Does not retrieve image data.
Inputs: sopInstanceUid (required), studyInstanceUid (required), seriesInstanceUid (required).
get-instance-metadataA
Retrieves and converts a DICOM instance to human-readable text. Requires Study, Series, and SOP Instance UIDs from find-instances. Does not retrieve image data.
Inputs: sopInstanceUid (required), studyInstanceUid (required), seriesInstanceUid (required).
get-structured-report-textA
Retrieves and converts a Structured Report (SR) instance to human-readable text. Requires Study, Series, and SOP Instance UIDs from find-structured-reports. Does not retrieve image data.
Inputs: sopInstanceUid (required), studyInstanceUid (required), seriesInstanceUid (required).
render-instance-frameA
Renders a specific frame from a DICOM instance to an image format. Requires Study, Series, and SOP Instance UIDs from find-instances, and a frame number. Returns the rendered image as a base64-encoded string.
Inputs: sopInstanceUid (required), studyInstanceUid (required), seriesInstanceUid (required), frame, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool targets a specific resource or action: studies, series, instances, encapsulated PDF reports, structured reports, and metadata/rendering. There is clear separation between find and get operations, and between different document types, preventing confusion.
All tool names follow a consistent verb-noun pattern with lowercase and hyphens (e.g., find-studies, get-instance-metadata, render-instance-frame). No mixing of conventions.
With 9 tools, the set is well-scoped for a DICOMweb server focused on querying and retrieving data. Each tool has a clear role, and the number aligns with typical best practices.
The server covers core query and retrieval operations for studies, series, instances, and special document types. Missing write operations (store, delete) and bulk retrieval, but for a read-oriented viewer, the surface is reasonably complete.
Maintenance
Related MCP Connectors
Hosted MCP server exposing US hospital procedure cost data to AI assistants
MCP server for searching Airweave collections with natural language queries.
Official remote MCP server for Archivist AI TTRPG campaign memory: characters, sessions, and more.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to query and analyze medical imaging metadata from DICOM servers, including patient information, studies, series, and instances, as well as extract text from encapsulated PDF documents.108MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query, read, download, and move medical imaging data on DICOM servers (PACS, VNA) including patient searches, study retrieval, PDF report extraction, and image transfer to AI endpoints for analysis.MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for reading C2PA content provenance manifests from media files, enabling natural language queries about AI-generated content, signatures, and provenance.3MIT
- AlicenseBqualityDmaintenanceAn MCP server that lets AI assistants read and visually analyze local documents — PDFs, Excel spreadsheets, CSV files, Word documents, PowerPoint presentations, and images.449 npm100 PyPIMIT