How to Use the BallDontLie MCP in Pydantic AI

Force strict runtime validation on NBA data using Pydantic AI and your preferred LLM.

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 Pydantic AI

Create your Vinkius account to connect BallDontLie to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe box scores in Pydantic AI

Sports APIs change without warning. If an endpoint suddenly drops a field, you want your system to fail loudly. Connect this MCP Server and your agent validates every `get_game_details` response against your exact Pydantic models. No silent corruption makes it into your database. If the agent expects an integer for points and gets a string, the framework throws a validation error immediately. You fix the model, not a polluted dataset.

Model-agnostic player scouting

Lock in your data structures, then swap models whenever you want. You can use Anthropic to query `list_players` today and switch to a local Llama model tomorrow. The validation layer stays identical. The framework executes `get_player_details` and forces the LLM to map the raw JSON into your strict schema. You care about correctness above all else, and this guarantees it.

Build reliable season aggregates

Calculating metrics requires clean inputs. Your agent hits `get_season_averages` and `list_teams` to build a complete picture of the league. Every single float and string gets checked at runtime. Setup takes minutes with the unified MCPToolset class. Point it at your Vinkius HTTP endpoint, pass it to your agent, and start pulling type-checked sports data instantly.

Setup guide

Set up BallDontLie MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "balldontlie-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to BallDontLie tools.",
)

result = await agent.run("List recent BallDontLie transactions")
print(result.output)

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 Pydantic AI

Install the slim package with MCP support. Initialize an MCPToolset with your Vinkius HTTP URL and add it to your agent's toolsets array.

Yes. If you require a specific rebound metric and the API omits it, the framework throws a loud validation error. It prevents bad data from corrupting your downstream systems.

No. The framework is completely model-agnostic. You can run these NBA queries through OpenAI, Gemini, or a local open-weight model without changing your tool setup.

The older HTTP class is deprecated. The unified MCPToolset handles both Streamable HTTP and SSE transports cleanly, making your connection to Vinkius much more stable.

We run every connection through a zero-trust V8 Isolate Sandbox. Your strict schemas and the retrieved NBA player statistics exist in an ephemeral environment that vanishes the second the request completes.

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