How to Use the BallDontLie MCP in Vercel AI SDK

Q: How do I initialize the BallDontLie tools in my Vercel AI SDK setup?

Install @ai-sdk/mcp and run createMCPClient using your Vinkius HTTP endpoint. Pass the client tools directly into streamText or generateText to let your agent query NBA statistics.

Q: Do I need to close the connection after querying BallDontLie?

Yes, always call mcpClient.close() when your execution finishes. This cleans up the active server-sent events or HTTP connections and prevents memory leaks in your serverless functions.

Stream real-time NBA stats directly into your Next.js frontend with the BallDontLie MCP Server and 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 BallDontLie MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Player Profiles with Vercel AI SDK

The `list_players` and `get_player_details` tools let your AI client search the NBA database and pull specific athlete profiles. By pairing these tools with the Vercel AI SDK, you render player heights, weights, and positions live on screen as the model finds them. You write UI code that maps these raw JSON payloads to React components. Instead of waiting for a slow backend fetch, your users watch the NBA player card build in real-time inside their Vercel AI SDK chat window.

Live-Render NBA Season Averages

Running `get_season_averages` pulls year-by-year stat lines for any active NBA player, while `list_player_stats` gives you game-by-game breakdowns. Your Vercel AI SDK frontend streams these NBA numbers straight into charts using standard UI components. Because this MCP Server runs on Vinkius edge-compatible infrastructure, your Next.js edge routes process the NBA data with zero cold-start delay. This setup lets Vercel AI SDK users get instant answers about shooting percentages or rebounds without staring at a loading spinner.

Real-Time Game and Team Data Streams

Calling `list_games` and `get_game_details` fetches schedule info and match results, while `get_team_details` and `list_teams` handle franchise metadata. Your Vercel AI SDK client calls these tools to query the MCP server for NBA matchups or divisional standings. The Vercel AI SDK handles the transport layer automatically, feeding raw NBA team records and game scores directly into your streaming text output. You get clean JSON structures that you can immediately pipe to your custom basketball widgets.

Setup guide

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

Install `@ai-sdk/mcp` and run `createMCPClient` using your Vinkius HTTP endpoint. Pass the client tools directly into `streamText` or `generateText` to let your agent query NBA statistics.

Yes, this MCP Server works perfectly on Edge Functions. The Vinkius hosted endpoint handles the heavy lifting, allowing your edge routes to execute light HTTP requests for NBA data.

Vinkius manages the underlying API keys and connection pools to prevent rate-limit failures. Your SDK code just handles the streamed responses, while our infrastructure keeps the NBA data pipeline open.

Yes, always call `mcpClient.close()` when your execution finishes. This cleans up the active server-sent events or HTTP connections and prevents memory leaks in your serverless functions.

Your queries only touch public NBA player, team, and game statistics. Vinkius isolates your session inside a secure V8 sandbox, ensuring no personal application tokens or user queries are logged or exposed to third parties.

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