How to Use the Epic Fhir MCP in Vercel AI SDK

Q: Can I use this to search for patients in Epic Fhir from my Vercel AI SDK app?

Yes. The searchpatients tool is designed for exactly that. Your agent can take a name or MRN from your UI, call the tool, and stream the matching patient records back to your application.

Stream patient data from Epic directly into your Next.js app with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Epic Fhir MCP to Vercel AI SDK

Create your Vinkius account to connect Epic Fhir to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Epic Fhir with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Patient Dashboards

This MCP server connects your Vercel AI SDK app to Epic's FHIR API. You can pull a patient's entire history—conditions, meds, labs—and stream it right into your React components. The user sees data populate in real time. You can use `get_patient` to fetch demographics, then fire off parallel calls to `list_medications` and `list_allergies`. Since the AI SDK streams tool output, your UI updates instantly as each piece of data arrives. It's a much better user experience.

Search and Display Patient Records

The `search_patients` tool lets you build a type-ahead search for your users. They can find patients by name or MRN, and your UI can display the results as they type. It feels fast because it is. Once a patient is selected, you can grab their upcoming visits with `list_appointments` or past visits with `list_encounters`. You're not just getting data; you're building a responsive clinical interface.

Review Clinical Data with the AI SDK

Give your agent the tools to assemble a full clinical picture. It can use `list_diagnostic_reports` to find recent lab work and `list_conditions` to check for active diagnoses, all from a natural language prompt. Your agent can then summarize its findings for the user. Because this is an MCP server, all the messy FHIR API authentication and data parsing is handled for you. You just get clean JSON to work with.

Setup guide

Set up Epic Fhir MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Epic Fhir tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Epic Fhir transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Epic Fhir. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Epic Fhir now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Epic Fhir MCP in Vercel AI SDK

You connect the Vercel AI SDK to the MCP server's endpoint. Your agent can then call tools like `list_medications`. The results stream back through the SDK, letting you render them live in your frontend app.

Yes. The `search_patients` tool is designed for exactly that. Your agent can take a name or MRN from your UI, call the tool, and stream the matching patient records back to your application.

You get access to core patient data. This includes demographics with `get_patient`, current problems with `list_conditions`, immunizations with `list_immunizations`, and lab results via `list_observations`.

Yes. Vinkius manages the connection to the Epic FHIR API. Your Vercel AI SDK app uses a single, ephemeral token to talk to the server, so your frontend code never touches raw API credentials.

This server only accesses the patient data needed for a specific tool call, like `list_diagnostic_reports` or `list_appointments`. The data is streamed through Vinkius's zero-trust environment and is not stored. Your app's connection is secured via its unique endpoint token.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript