How to Use the CMS.gov Data MCP in Vercel AI SDK

Q: How do I stream CMS.gov Data results using Vercel AI SDK and MCP?

Install @ai-sdk/mcp and initialize the client with your Vinkius HTTP endpoint. Pass the tools from mcpClient.tools() directly into streamText to let your LLM query Medicare providers in real-time.

Q: Do I need to manually close the connection after searching nursing homes?

Yes, always call mcpClient.close() when your query completes to free up active connections. This keeps your serverless functions clean and prevents memory leaks during active searches.

Stream real-time Medicare provider details and hospital ratings directly into your Next.js UI using the 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 CMS.gov Data MCP to Vercel AI SDK

Create your Vinkius account to connect CMS.gov 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 CMS.gov Data with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live-streaming doctor search directories

The `search_doctors` tool lets your AI client find Medicare-enrolled clinicians and stream their NPIs and active status directly to your user interface. By feeding this tool into Vercel AI SDK's streaming text function, your frontend renders matching physician names and practice addresses letter-by-letter as they come back from the CMS database. Users don't wait around for a full database query to finish loading. You use `search_providers_by_specialty` to let patients filter cardiologists or dermatologists, updating the React state on the fly without blocking the main thread.

Run hospital quality ratings via MCP Server

The `get_hospital_ratings` tool extracts quality metrics, emergency services, and general classifications for any medical facility in the country. Hooking this MCP Server up to your Edge runtime means you fetch star ratings without cold starts or heavy server-side overhead. Call `search_hospitals` inside a lightweight Vercel route to let users check local emergency rooms. The SDK handles the raw JSON payload and formats it into clean, readable UI components instantly.

Render live dataset metadata directly in your UI

The `list_datasets` tool pulls the latest open data catalogs from CMS, including publication dates and modification timestamps. You pass these tools directly into `streamText` so your application can display real-time updates on Medicare utilization. Fetch detailed descriptions with `get_dataset_metadata` when a user clicks a dataset ID. The Vercel AI SDK handles the active connection, meaning your interface stays snappy while pulling massive government indexes.

Setup guide

Set up CMS.gov 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 CMS.gov 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 CMS.gov 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 CMS.gov Data. 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 CMS.gov 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 CMS.gov Data MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client with your Vinkius HTTP endpoint. Pass the tools from `mcpClient.tools()` directly into `streamText` to let your LLM query Medicare providers in real-time.

Yes, this setup is fully compatible with Edge Functions. The lightweight MCP Server client connects via standard HTTP, letting you search hospitals and doctors without cold-start delays.

Vinkius manages the secure API handshake on its end. You just pass your single endpoint token in the `createMCPClient` transport configuration, avoiding any complex government portal setups.

Yes, always call `mcpClient.close()` when your query completes to free up active connections. This keeps your serverless functions clean and prevents memory leaks during active searches.

This server only touches public CMS.gov data, including public NPIs, hospital star ratings, and nursing home addresses. Vinkius runs the query in a secure, isolated V8 sandbox, ensuring no private search parameters leak to the public web.

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