Supports publishing the MCP server as an npm package for distribution and installation
Click on "Install 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., "@MedGemma Vertexinterpret this chest X-ray for signs of pneumonia"
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.
MCP Medical Imaging
MCP server that routes medical questions and images to MedGemma models hosted on Vertex AI.
answer_med_text → MedGemma-27B (text-only)
answer_med_image → MedGemma-4B-IT (multimodal)
Quick start
# 1. Install deps
npm install
# 2. Configure env vars (see .env.example)
export VERTEX_PROJECT=your-gcp-project-id
export ENDPOINT_27B=1234567890123456789
export ENDPOINT_4B=9876543210987654321
# 3. Run in dev mode (stdio+HTTP on :4000)
npm run devAdd this to Claude Desktop servers.json:
{
"id": "medgemma",
"name": "MedGemma Vertex",
"transport": "http",
"url": "http://localhost:4000/mcp"
}Related MCP server: Vertex AI MCP Server
Publishing
The package is automatically compiled on npm publish (see prepublishOnly).
npm login # once, with your npm credentials
npm version patch # bump version
npm publish --access publicLicense
Code: Apache-2.0. MedGemma model usage subject to Health AI Developer Foundations license.