---
title: "AWS Labs HealthImaging: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/awslabs-healthimaging/
description: "Searches and manages medical imaging datastores, image sets and DICOM lifecycle operations."
---

# AWS Labs HealthImaging: review, setup & limitations · Undominated.ai

> Searches and manages medical imaging datastores, image sets and DICOM lifecycle operations.

[← Explore all mcp servers](/mcp-servers/)

AWS DATA SERVICES / AWS Labs

# AWS Labs HealthImaging

Searches and manages medical imaging datastores, image sets and DICOM lifecycle operations.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/awslabs/mcp)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 7 linked sources
 Publisher AWS Labs
 Licence [Apache-2.0 ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE)
 Revision 8840003820a7
 [Read what was—and wasn’t—checked ↓](#review)

“The AWS HealthImaging MCP Server enables AI assistants to interact with AWS HealthImaging services through the Model Context Protocol (MCP).”

 [AWS Labs · upstream description ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Specialized publisher integration with documented IAM and data access boundaries.
- Inspect image-set metadata and import-job status in an authorized test datastore.
- The catalogue does not already have src/healthimaging-mcp-server/README.md.
- The README documents irreversible image-set deletion and patient-study deletion, and the install examples do not pass a read-only flag.

### A good fit for

 - Inspect image-set metadata and import-job status in an authorized test datastore.
- Review a carefully scoped imaging lifecycle change with explicit patient/study identifiers.
- Inspecting HealthImaging metadata only after the caller withholds the delete tools the README lists

### Weigh up before choosing

 - The inspected server registers destructive datastore, study, series, instance and bulk-deletion tools without a global read-only startup gate. Use read-only IAM for inspection.
- Returned metadata and image frames can contain patient information; publisher HIPAA considerations are not compliance certification of this client deployment.
- Import/export operations require appropriate S3 locations and service roles; metadata modification or deletion can affect multiple records.
- The monorepo now recommends Agent Toolkit for AWS for production. This specialized local server remains documented; its leaf and root documentation were checked for deprecation.
- This review did not execute the resource.
- Pinning commit 8840003820a78dd018561d55c7ab12fcdd708464 does not verify transitive dependencies.
- No read-only flag appears in the README. The pip line and the uvx JSON do not disable delete_image_set, delete_patient_studies, or bulk_delete_by_criteria.
- The only occurrence of stdio is inside the VS Code install-badge URL as an encoded type field. The Linux JSON block does not set type.
- The license section says Apache License, Version 2.0. The repository LICENSE text is Apache License Version 2.0.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - src/healthimaging-mcp-server/README.md
- src/healthimaging-mcp-server/pyproject.toml
- src/healthimaging-mcp-server/awslabs/healthimaging_mcp_server/server.py
- Root README.md and LICENSE
- LICENSE

### Our findings

 - Pinned server.py has unconditional tool registrations for create_datastore, delete_datastore, bulk_delete_by_criteria and retrieval operations. No read-only argument was identified in its startup.
- The overview says 39 specialized tools, and a later sentence says 39 tools in eight categories. It also says 21 standard API operations and 18 advanced DICOM operations, which sum to 39.
- Counted in this file, the eight category headings sum to 36. The bullet lines under them sum to 38: Datastore Management says 4 tools and lists 3, and Data Analysis Operations says 8 tools and lists 11. The other six headings match their bullet counts.
- delete_image_set is marked IRREVERSIBLE. delete_patient_studies, delete_study, and bulk_delete_by_criteria are also listed. The word readonly does not appear, and read-only does not appear.

### Not established by this review

 - Server startup, authentication, live tool execution and security isolation were not tested.
- Published package/container parity with a source revision and hosted implementation internals were not tested.
- The resource was not executed and its tools were not called.
- No HealthImaging API call was made.
- The tool bullets were counted in the README and were not listed from a running server.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/README.md)

DOCUMENTED COMMAND

 uvx awslabs.healthimaging-mcp-server@latest Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - Configure a read-only AWS role and the intended HealthImaging region before first connection.
- List and inspect the exact datastore/image-set identifiers; keep broad delete and bulk update operations outside routine diagnostics.
- For an approved transfer or mutation review S3 destinations, role permissions, version selection and returned job status.

### Before you start

 - Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process.
- An AWS account, configured credentials and access to the intended region and service resources.

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "awslabs-healthimaging": {
 "command": "uvx",
 "args": [
 "awslabs.healthimaging-mcp-server@latest"
 ],
 "env": {
 "AWS_PROFILE": "YOUR_RESTRICTED_PROFILE",
 "AWS_REGION": "us-east-1"
 }
 }
 }
} Copy configuration ↗

### Compatibility

Python 3.10 or newer, uv/uvx and an MCP client that can launch a local stdio process. · An AWS account, configured credentials and access to the intended region and service resources. · Cursor · VS Code · Kiro · Cline

### Implementation

Python · python

### Transports

stdio

### AWS data services

 - Reads imaging content and, where IAM permits, creates/deletes datastores, edits metadata, transfers DICOM data and performs bulk deletions.
- List and search datastores and image sets
- Create datastores, import and export DICOM, update metadata, and delete image sets or studies
- Does not document an IAM user, role, group, policy, or access-key tool

### Cost model

AWS service, model, query and storage charges apply; running the MCP process does not include those services.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Publisher setup, capabilities and operating boundaries ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/pyproject.toml) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/pyproject.toml Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/awslabs/healthimaging_mcp_server/server.py) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/awslabs/healthimaging_mcp_server/server.py Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Pinned package and implementation ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Applicable licence ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE Supports: license
- [HealthImaging MCP README ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/README.md) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/src/healthimaging-mcp-server/README.md Supports: tool-count mismatch and delete tools
- [Repository LICENSE ↗](https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE) Checked 2026-10-14 https://github.com/awslabs/mcp/blob/8840003820a78dd018561d55c7ab12fcdd708464/LICENSE Supports: Apache License Version 2.0

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### AWS Labs Amazon Translate ↗ Translates text and manages document translation jobs and custom terminology with AWS Translate.](/mcp-servers/awslabs-translate/)[### AWS Labs Finch ↗ Builds and pushes container images through the local Finch CLI, with additional ECR repository support.](/mcp-servers/awslabs-finch/)[### AWS Labs HealthLake ↗ Discovers HealthLake datastores and reads or manages FHIR resources, with an explicit read-only mode.](/mcp-servers/awslabs-healthlake/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
