Click on "Deploy 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., "@Virtual Patient MCP Server start the STEMI case, let me take a history and order a troponin"
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.
A full-stack Model Context Protocol (MCP) Application designed for medical students and doctors to practice clinical consultations in an emergency / ward setting.
+---------------------------------------------------------------------------------------+
| HOST PLATFORM (e.g., Enterprise Agent Chat / McpAppContainer) |
| • Renders <McpAppContainer resourceUri="http://localhost:5174" /> |
| • Listens to postMessage events (JSON-RPC 2.0 tools/call) |
+-------------------------------------------|-------------------------------------------+
|
postMessage (JSON-RPC 2.0)
|
+-------------------------------------------v-------------------------------------------+
| CLIENT: THE MCP APP (http://localhost:5174) |
| • Real-time Animated HTML5 Canvas ECG Monitor (Sinus Tachycardia / STEMI rhythm) |
| • History Taking Chat (Anamnesis) with rapid clinical chips & custom inquiries |
| • Targeted Physical Examination Suite (Mitral Apex, JVP, Lung Bases, Chest Wall) |
| • Diagnostic Lab Center (12-Lead ECG strip, Troponin I STAT, CXR, CBC, BMP) |
| • Resuscitation & Rx Pad (Aspirin chewable, Sublingual Nitroglycerin, Oxygen) |
| • Official OSCE Scorecard (Letter grade, competency checklist, professor debrief) |
+-------------------------------------------|-------------------------------------------+
|
REST / SSE / stdio Transports
|
+-------------------------------------------v-------------------------------------------+
| SERVER: VIRTUAL PATIENT MCP SERVER (http://localhost:3001) |
| • Model Context Protocol Server (@modelcontextprotocol/sdk) |
| • Tools: converse_patient, examine_patient, order_investigation, |
| administer_medication, submit_consultation, switch_case |
| • Resources: patient://vitals, patient://chart |
| • Medical Cases Engine: loads cases from /cases/*.json |
+---------------------------------------------------------------------------------------+Related MCP server: Konsilium
npm run devMCP Server: http://localhost:3001 (SSE: /sse, REST: /api/state)
Interactive MCP App: http://localhost:5174
McpAppContainerIn your agent chat interface, pass:
<McpAppContainer
resourceUri="http://localhost:5174"
minHeight={650}
onToolCallRequested={(call) => {
console.log("MCP Tool Call from Virtual Patient UI:", call);
}}
/>Tool Name | Parameters | Description |
|
| Conducts history-taking. Patient responds with emotional fidelity without leaking diagnosis. |
|
| Elicits physiological examination findings (auscultation sounds, palpation tenderness). |
|
| Releases laboratory panels and imaging reports (12-lead ECG, Troponin I, CXR). |
|
| Gives emergency pharmacotherapy and triggers immediate telemetry & pain updates. |
|
| Concludes encounter and generates the comprehensive OSCE scorecard. |
|
| Switches between clinical cases (e.g. STEMI vs. Community-Acquired Pneumonia). |
case_01_stemi.json — 58-year-old male with acute retrosternal crushing chest pain radiating to left arm/jaw (Acute STEMI).
case_02_pneumonia.json — 42-year-old female with high fever, rigors, rusty sputum, and pleuritic chest pain (Community-Acquired Pneumonia).
This server cannot be deployed
Healthcare staffing simulator — ED, walk-in clinic, and appointment office DES tools.
Physician-reviewed medical opinions and prescriptions for AI agents.
Licensed US telehealth — GLP-1 medications, intake, consents, Stripe ACP. HIPAA-compliant, 30 tools.
Patient, meal plan, prescription, chart and anthropometry management for dietitians.
