Healthcare 3D

Community

MCP server for Healthcare & Medical 3D visualization — anatomy viewers, molecular structures, DICOM medical imaging, surgical planning, dental scanning.

How to install ↓ Compare GitHub source repository ↗

Category: Other #205 of 230
Stars: ★ 1.3k Very popular
Transport: stdio (local process)
Runtime: Node.js
Credentials: No credential needed
License: Apache-2.0
Last commit: 1 day ago

35FMRS · D

This MCP server focuses on healthcare 3D visualization, with a clear tool set, but official docs do not detail tool specifics. As part of the SceneView ecosystem, it suits AI-assisted development in medical domains, but users should verify actual tool behavior and output.

Strongest · Maintenance 12/20 Weakest · Reliability 3/20

Reliability

3/20

Security and permissions

5/20

Maintenance

12/20

Documentation

7/20

Setup experience

8/20

Why each score

Reliability 3/20: Evidence consists only of the manifest and README; no source, tests, or CI artifacts for the healthcare server were provided. The README claims 7 tools and the manifest declares an npm package over stdio, but startup, MCP handshake, and whether the declared tools match real behavior cannot be verified. Static calibration caps reliability at 12, and uncertainty lowers the score, so a conservative 3 is given.
Security and permissions 5/20: No malware, real secrets, or obvious overreach were found, so no red line is triggered. However, there is no source or documentation describing credential handling, network access, data boundaries, least privilege, or confirmation for dangerous operations. These gaps are especially significant for DICOM/medical data. Since core security properties cannot be assessed, the score is 5.
Maintenance 12/20: The repository as a whole shows an Apache-2.0 license, CI badge, releases/changelog, Discord, and sponsors, indicating an active project with clear ownership. But no server-specific commit history, issue response, dependency updates, or independent release evidence exists for healthcare-3d-mcp; version 1.1.0 is known only from the manifest. Therefore the score is 12, not higher.
Documentation 7/20: The README gives the server's name, purpose, install command, and a claimed tool count of 7, but lacks tool parameters, authentication, limits, cost, and troubleshooting guidance. No dedicated documentation for this server was provided. The 7 tools cannot be verified against real schemas, so the documentation is only minimally usable; score 7.
Setup experience 8/20: The install command npx healthcare-3d-mcp is clear, and the manifest provides the npm identifier and stdio transport, giving a definite installation path. However, there are no client configuration examples, platform compatibility notes, end-to-end connection steps, or execution evidence proving the install works. Static calibration caps setup at 15; a conservative score of 8 is assigned.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

Best for

AI-assisted development for rapid healthcare 3D visualization
Developers integrating medical 3D features into their apps
Tool development for medical education, surgical planning, etc.

Not for

General-purpose 3D scene development (use main SceneView MCP)
Standalone apps requiring real-time rendering or high-performance interaction (this server assists code generation, not direct rendering)
Non-medical domain users

Required permissions

Requires network access to download package from npm
May access local file system to read DICOM or other files (depending on tool implementation)
No explicit special permissions required

Risks and side effects

AI-generated code may contain compilation or runtime errors, requiring human review
Involves medical data; ensure privacy compliance and avoid leaking patient information
Dependency on npm package poses supply chain risks; update regularly

Setup

Before you start

Runtime：Node.js

claude mcp add healthcare-3d -- npx healthcare-3d-mcp
Or manually add to MCP config file.

claude_desktop_config.json

{
  "mcpServers": {
    "healthcare-3d": {
      "command": "npx",
      "args": [
        "-y",
        "healthcare-3d-mcp"
      ]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "healthcare-3d": {
      "command": "npx",
      "args": [
        "-y",
        "healthcare-3d-mcp"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add healthcare-3d -- npx -y healthcare-3d-mcp

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After installing via npx healthcare-3d-mcp, the client's tool list should show the server's 7 Healthcare 3D tools; alternatively ask the assistant to list its available healthcare-3d tools to confirm the connection.

Troubleshooting

Check that npm is installed and version is correct
Confirm MCP client (e.g., Claude Desktop) is configured correctly with command npx healthcare-3d-mcp
If tools are unresponsive, check network connection or npm registry
Ensure latest version: npm show healthcare-3d-mcp version

Things to try

Once connected, you can ask your AI assistant things like:

Build me a 3D anatomy viewer app using SceneView
Create a sample that visualizes DICOM medical imaging in 3D
Generate Android code for a dental scanning 3D viewer
Show me an AR surgical planning scene example

Use cases

Generate 3D visualizations of anatomical structures

Display molecular 3D models

Load and view DICOM medical images

Assist surgical planning with 3D views

Visualize dental scan data

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

This MCP server is a specialized tool for healthcare and medical 3D visualization scenarios, built on the SceneView SDK. It offers anatomy viewers, molecular structures, DICOM medical imaging, surgical planning, and dental scanning. The server is a standalone MCP server (package healthcare-3d-mcp), independent from other MCP servers in the SceneView repository (e.g., automotive, gaming). It is published via npm, uses stdio transport, and is mainly used to assist AI assistants in generating healthcare-related 3D visualization code.

Similar servers

Hevy MCP 77 · B

Manage your Hevy workout data from AI assistants via MCP.

★ 509 · Tools 26 Compare with this →

Firecrawl MCP Server 75 · B

Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents

★ 7.6k · Tools 11 Compare with this →

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →

Compartment 75 · B

Encrypted, fully offline long-term memory for AI agents

★ 579 · Tools 14 Compare with this →

Compare with other MCP servers

More servers from this repository

Source revision 5867681d6163 Data synced 2026-10-12 Read the FMRS scoring method