How to Use the NHL MCP in Vercel AI SDK

Q: How do I stream live NHL scores using the Vercel AI SDK?

You install @ai-sdk/mcp and configure the MCP client to point to the Vinkius endpoint. Then, pass the tools from getlivescores into streamText to let the model fetch and render the live game data on the fly.

Q: Can I use Vercel AI SDK to compare historical NHL player stats?

Yes. Your model can call getskatersummary and getgoaliesummary to retrieve season-long metrics. The SDK then formats these numbers into side-by-side comparison tables in your frontend.

Q: How do I close the connection to the hockey data server?

Always call mcpClient.close() once your MCP connection finishes. This prevents memory leaks on your serverless edge functions and keeps your connection pool clean.

Pipe live NHL stats and real-time game scores directly into your React or 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 NHL MCP to Vercel AI SDK

Create your Vinkius account to connect NHL 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 NHL with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live NHL scores with Vercel AI SDK

Stop making your users wait for page refreshes or spinner wheels. This MCP Server lets your AI client pull active game data using `get_live_scores` and feed it directly to the Vercel AI SDK streaming engine. Your users see goals, penalties, and period updates appear on their screens as they happen. You set up the connection once and let the SDK handle the rest. By combining `get_current_schedule` with live tracking, your application renders dynamic hockey dashboards that update without blocking the main thread.

On-Demand Player Profiles and Stats

Building a fantasy hockey interface requires quick access to deep player histories. Your application can now call `get_player_landing` and `get_skater_summary` to instantly populate player cards during a chat session. The SDK handles these tool calls on the edge, keeping latency low. When a user asks about a skater's recent performance, the model fetches the exact data points and streams the formatted profile straight to the component.

Deep-Dive Historical Game Analysis

Go beyond basic boxscores by letting your model fetch complete historical records. Using this MCP Server, you can build tools that dissect past matchups down to individual shifts and shots with `get_game_boxscore` and `get_game_play_by_play`. This setup lets your interface present detailed post-game breakdowns. The model parses the raw feed, extracts key turning points, and presents a clean summary to the hockey fan.

Setup guide

Set up NHL 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 NHL 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 NHL 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 NHL. 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 NHL 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 NHL MCP in Vercel AI SDK

You install `@ai-sdk/mcp` and configure the MCP client to point to the Vinkius endpoint. Then, pass the tools from `get_live_scores` into `streamText` to let the model fetch and render the live game data on the fly.

Yes. Your model can call `get_skater_summary` and `get_goalie_summary` to retrieve season-long metrics. The SDK then formats these numbers into side-by-side comparison tables in your frontend.

It handles them easily because the server runs on V8 isolates. The model calls `get_current_schedule` to pull today's matchups and streams the JSON payload directly into your edge-rendered UI components.

Always call `mcpClient.close()` once your MCP connection finishes. This prevents memory leaks on your serverless edge functions and keeps your connection pool clean.

Yes, because we only touch public NHL statistics, player bios, and game schedules via our MCP Server architecture. No personal user data or proprietary source code is ever sent to the external sports database.

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