How to Use the NHL MCP in AutoGen

Q: How do I load the NHL tools into my AutoGen agents?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams to fetch the tool list, then pass that directly into your AssistantAgent constructor.

Deploy AutoGen multi-agent systems to debate hockey analytics and scout player matchups.

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 AutoGen

Create your Vinkius account to connect NHL to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live data to debating agents via MCP

The `get_team_powerplay` and `get_team_faceoff_percentages` tools give your AutoGen agents hard numbers to argue over. You assign one agent to act as an offensive coordinator and another as a defensive analyst. They pull the stats, review the percentages, and debate the best strategy for the upcoming game. The conversation continues until they reach a consensus. The offensive agent points out a weak penalty kill using `get_team_summary`, while the defensive agent counters with recent goalie performance data. You watch them negotiate the final scouting report.

Automate deep roster analysis

Your agents use `get_team_roster` and `get_player_landing` to evaluate line combinations. One agent suggests a trade based on salary cap assumptions, and the other verifies the player's actual production by querying their biographical and statistical profile. This setup prevents single-point failures in logic. If an agent misinterprets a player's shooting percentage, a peer agent double-checks the API response and issues a correction before finalizing the output.

Cross-reference historical milestones

Tools like `get_records_trophies` and `get_legacy_player_stats` let your agents compare eras. You prompt the system to evaluate a current star against a retired legend. The agents pull the historical data, adjust for era scoring rates, and argue the merits of both players. The system handles schema conversions automatically via `McpToolAdapter`. Your agents just request the data they need, read the JSON responses, and focus entirely on the debate.

Setup guide

Set up NHL MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes NHL tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="NHL_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NHL data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="NHL_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NHL data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` to fetch the tool list, then pass that directly into your `AssistantAgent` constructor.

Yes. Any agent configured with the tool adapter can execute a call. They can pull different endpoints at the same time to gather evidence for their arguments.

The API returns a validation error. The agent reads the error message, discusses the failure with its peers, and typically retries the call with corrected parameters.

No. The adapter handles the translation between the MCP Server schema and the agent's expected format. The agents read the raw JSON natively.

The agents only access public league records, venue details, and boxscores. Vinkius operates a zero-trust architecture, meaning your MCP token is authenticated securely and the server instance spins down immediately after the agents finish their debate.

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