How to Use the HealthData.gov (HHS Open Data) MCP in Vercel AI SDK

Q: How do I filter HealthData.gov (HHS Open Data) datasets using Vercel AI SDK?

Use the querydataset tool with SoQL parameters like $where or $select inside your model call. Your agent writes the query based on user input and streams the filtered JSON array back to the React UI.

Q: How do I initialize the MCP client connection in my project?

Install the core packages and use createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the returned tools directly into the tools parameter of your streaming function.

Stream public HHS health datasets directly into your React or Next.js frontend with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HealthData.gov (HHS Open Data) MCP to Vercel AI SDK

Create your Vinkius account to connect HealthData.gov (HHS Open Data) 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 HealthData.gov (HHS Open Data) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Catalog Search

Your app gets instant access to thousands of federal health datasets without maintaining a massive local database. By calling `get_catalog`, your AI client inspects the entire HHS public inventory on demand to find the exact dataset ID. The Vercel AI SDK streams these catalog results straight to the user's browser, bypassing stale caches. You don't have to write custom fetch wrappers or handle complex pagination logic manually.

Direct SoQL Queries from the Edge

Fetching specific healthcare metrics shouldn't require a heavy backend server. The `query_dataset` tool lets your agent run precise SoQL queries against real-time HHS endpoints directly from edge functions. This setup means your UI renders hospital capacity or disease tracking data in real time as the stream resolves. Users see raw figures and trends appear instantly, cutting down perceived latency to zero.

Zero-Lag UI Streaming with MCP Server Tools

Traditional apps force users to wait for a full API response before displaying any charts. This integration uses streamText to push dataset chunks directly into your component state as they arrive from the government servers. You control the flow by passing tools directly from the MCP Server to your model configuration. It closes automatically when the stream finishes, preserving serverless execution limits.

Setup guide

Set up HealthData.gov (HHS Open Data) 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 HealthData.gov (HHS Open Data) 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 HealthData.gov (HHS Open Data) 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 HealthData.gov. 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 HealthData.gov (HHS Open Data) 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 HealthData.gov (HHS Open Data) MCP in Vercel AI SDK

Use the `query_dataset` tool with SoQL parameters like `$where` or `$select` inside your model call. Your agent writes the query based on user input and streams the filtered JSON array back to the React UI.

Yes, the MCP client runs inside edge environments without issues. You invoke `get_catalog` to scan the metadata catalog, returning matching dataset IDs to your frontend stream within milliseconds.

Implement a simple caching layer or use SWR on the frontend to prevent repeated calls for static datasets. Since HHS updates most records weekly, fetching catalog metadata once per session keeps your API usage safe.

Install the core packages and use `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the returned tools directly into the tools parameter of your streaming function.

This tool only accesses public, non-PII health datasets hosted on HealthData.gov. No patient-identifying information is ever touched, processed, or stored by the Vinkius gateway or your local client.

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