How to Use the BallDontLie MCP in OpenAI Agents SDK

Q: Which OpenAI models work best with BallDontLie?

GPT-4o handles the complex JSON responses from getgamedetails perfectly. It maps the nested box score data to your agent's internal state without dropping fields.

Q: Does the OpenAI Agents SDK support handoffs with BallDontLie data?

Yes. You can have a researcher agent pull numbers via getseasonaverages and transfer control to a writer agent to format the final output.

Build production NBA analytics systems with the OpenAI Agents SDK using live game data and player stats.

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 OpenAI Agents SDK

Create your Vinkius account to connect BallDontLie to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed NBA stats directly into the OpenAI Agents SDK

Your production system needs hard numbers, not hallucinations. Connect this MCP Server to your OpenAI agent and it pulls exact game records using `list_games`. You get real box scores fed straight into your tracing dashboard. Handoffs work flawlessly for this use case. One agent can run `get_season_averages` to build a player profile, then pass that context to a specialized betting analysis agent. Everything runs under your strict guardrails.

Scout players and teams programmatically

Stop scraping poorly formatted sports sites. Your agent hits `list_players` to find specific athletes, then pulls their current roster status with `get_team_details`. Since OpenAI's framework handles tool discovery automatically, you just pass the Vinkius endpoint token. The agent figures out when to call `get_player_details` without you writing custom routing logic.

Build automated post-game reports

Nightly recaps require accurate box scores. Give your agent access to `list_player_stats` and it grabs every rebound, assist, and foul from last night's slate. Set your cache parameters and let the agent run. It compiles the raw data, applies your custom safety constraints, and generates a clean summary before you even wake up.

Setup guide

Set up BallDontLie MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all BallDontLie tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives BallDontLie tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate BallDontLie tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="BallDontLie Agent",
            instructions="You have access to BallDontLie tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to your Agent constructor's mcp_servers array.

Yes. Set cacheToolsList=True when configuring the MCP Server. That keeps your agent from repeatedly fetching the same schema data.

GPT-4o handles the complex JSON responses from get_game_details perfectly. It maps the nested box score data to your agent's internal state without dropping fields.

Yes. You can have a researcher agent pull numbers via get_season_averages and transfer control to a writer agent to format the final output.

Your prompt and this MCP Server run through a V8 Isolate Sandbox. Vinkius operates a zero-trust, ephemeral environment. We process the player stats and game logs, then instantly destroy the container.

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