Sample Prototype Packet - Build Global Longevity Japan 2026

0

What MCP is (60-second primer)

MCP (Model Context Protocol) is the "USB-C for AI apps"—a standard that lets assistants like Claude talk to small "servers" that expose tools and data you choose.

Claude Desktop (and others) can connect to your local or hosted MCP server with a tiny JSON config; the server declares tools like create_ticket, search_FAQ, appt_slots.

1

Choose your first use cases (10 minutes)

Start with low-risk, high-volume requests:

Medication refill intake (collect required fields, sanity checks, create a task)
Appointment options (read calendar slots and propose times)
Records request (collect identity + destination, generate a task)
FAQs (search a clinic FAQ doc and draft answers for staff approval)

Anything that touches PHI should draft and queue for human send-off.

2

Prerequisites (15 minutes)

Claude Desktop installed (Mac/Windows)
Node.js 18+ (for the TypeScript server)
A Google Sheet or lightweight DB (even a JSON file) to store request tickets
Optional: A starter MCP server template (TypeScript)

3

Scaffold a minimal MCP server (30-40 minutes)

A. Create a folder

mkdir mcp-patient-requests && cd mcp-patient-requests
npm init -y
npm install @modelcontextprotocol/sdk zod
npm install -D typescript ts-node @types/node
npx tsc --init
        

B. Add src/server.ts — two tools to start:

create_request → validates and writes a ticket to data/requests.json
list_requests → returns open tickets for follow-up

import { Server, Tool } from "@modelcontextprotocol/sdk/server";
import { z } from "zod";
import { readFileSync, writeFileSync, existsSync, mkdirSync } from "fs";

const server = new Server({ name: "patient-requests", version: "0.1.0" });

const RequestSchema = z.object({
  type: z.enum(["refill", "appointment", "records", "question"]),
  patient_name: z.string(),
  contact: z.string(),
  details: z.string().optional()
});

// ... implementation details
        

C. Add scripts in package.json

"scripts": { "dev": "ts-node src/server.ts" }

D. Run it

npm run dev

Why this works: The server exposes two MCP tools that any MCP-aware assistant can call. The assistant stays the UI; the server is your guard-railed gateway to actions/data.

4

Connect it to Claude Desktop (5 minutes)

Edit the Claude config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "patient-requests": {
      "command": "npx",
      "args": ["-y", "ts-node", "src/server.ts"],
      "cwd": "/absolute/path/to/mcp-patient-requests"
    }
  }
}
        

Restart Claude Desktop. You should see patient-requests available as a tool.

5

Use it in plain English (2 minutes)

Try in Claude:

"Use patient-requests → create_request for a refill.
Name: Jane Doe. Contact: jane@example.com
Details: Needs 30-day refill of levothyroxine 75 mcg; last seen 3 months ago."
        

Then:

"Use patient-requests → list_requests (open). 
Summarize what needs staff action and draft a response for each."
        

Pattern: The assistant does the reasoning + drafting; the MCP tool logs/queues. Staff reviews and sends.

6

Add useful tools next (30-60 minutes total)

FAQ search (no PHI): Add search_faq(query) that loads a local faq.json
Scheduling preview (read-only): Add get_slots(provider, days_ahead) that reads shared calendar
Refill safety checklist: Add refill_policy_check(med) to return clinic's checklist
Status updates: Add update_request(id, status) to close out items

7

Governance & Safety (non-negotiable)

No direct PHI to vendors unless you have BAAs; keep this server local or VPC
Least privilege: expose read-only versions first (FAQ, slots)
Logging: keep a local audit log of tool calls + inputs
Config hygiene: Claude Desktop reads a simple JSON config—limit each server's access
Stay current on MCP security guidance as adoption grows

8

Optional: Host & Share (later)

You can deploy the same server behind an HTTPS process and point multiple MCP hosts at it (e.g., ops staff + intake coordinator). Many teams start local, then move to a small VM.

9

What this unlocks in clinic (week 1 wins)

Single "front door" for patient requests that your AI can see and act on
Faster triage: assistant drafts + MCP logs → staff approves
Consistent policy adherence via checklists the assistant pulls in every time
Searchable trail of requests (JSON/CSV) for QA and ops metrics

10

Demo script (you can literally read this)

Open Claude; show patient-requests tool
Say: "Create two test tickets (refill + appointment)."
Ask: "List open tickets; cluster by type; draft staff replies."
Show the JSON file filling up and your audit log
Close a ticket with update_request
End with a slide: "Next tools: FAQ, slots, policy checks."

Ready to implement?

This prototype packet is exactly what you'll receive from our hands-on AI workshops.

Secure Your Spot at Japan 2026 Limited to 300 builders and practitioners

Playbook: Patient Requests via MCP