How to Use the NHL MCP in Pydantic AI

Q: Can Pydantic AI handle raw NHL feed data?

Yes. You can map the output of getlegacygamelivefeed to a complex Pydantic model. This allows your agent to parse nested game events safely.

Validate all NHL data at runtime using Pydantic AI and strict schema enforcement.

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 Pydantic AI

Create your Vinkius account to connect NHL 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 NHL with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly typed NHL data for Pydantic AI

Every response from `get_goalie_summary` passes through your Pydantic models before the agent touches it. If the API returns unexpected values, the agent halts immediately to prevent data corruption. This setup guarantees that your agent logic only runs on verified data. You know exactly what fields are present because the schema validation catches mismatches instantly.

Reliable stat tracking in Pydantic AI

Your agent pulls skater metrics via `get_skater_realtime` and validates them against your custom classes. This ensures your agent works with clean, predictable floating-point numbers and strings. By enforcing these types, you eliminate the risk of hallucinated fields. Your agent behaves predictably because the data contract is enforced on every single call.

Operational schedule and venue tools

Query `get_venues` and `get_current_schedule` to build localized event calendars. Your agent verifies every schedule detail against your defined Pydantic types. This approach keeps your application stable even if the underlying league format changes. Your agent will flag validation errors if the response structure doesn't match your expected model.

Setup guide

Set up NHL 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": {
        "nhl-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NHL 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 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 Pydantic AI

Define your Pydantic models to match the tool output. The framework automatically validates the data returned from the MCP Server before your agent processes it.

Yes. You can map the output of `get_legacy_game_live_feed` to a complex Pydantic model. This allows your agent to parse nested game events safely.

The agent will raise a validation error immediately. This prevents your application from executing logic based on corrupt or unexpected information.

The server supports both Streamable HTTP and SSE. You can choose the transport that fits your environment while maintaining full type safety.

The server acts as a strictly defined interface. It transmits public league data directly to your agent, ensuring no sensitive information is stored or exposed during the validation process.

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