How to Use the NHL MCP in LangChain

Q: How do I connect the NHL tools to my LangChain agent?

Run pip install langchain-mcp-adapters langgraph. Initialize a MultiServerMCPClient with your endpoint URL, call client.gettools(), and pass the array to your agent constructor.

Q: Does my LangChain setup remember past NHL queries?

Not by default. You need to use client.session() to maintain persistent context if your agent needs to reference a boxscore it pulled three turns ago.

Build multi-step hockey analytics pipelines using LangChain agents to query live scores, player stats, and historical records.

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 LangChain

Create your Vinkius account to connect NHL to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe live game data through your LangChain MCP Server

The `get_live_scores` and `get_game_play_by_play` tools feed realtime match events directly into your reasoning chains. Your agent pulls the current score, checks the play-by-play feed for recent penalties, and passes that context to the next prompt. You decide exactly how the agent reacts to a sudden shift in momentum. LangSmith tracks every call you make. If an agent loops while trying to parse `get_legacy_game_live_feed`, you see the exact token usage and latency. You fix the prompt, test the chain again, and watch the execution time drop.

Chain historical milestones to current performance

Tools like `get_records_milestone_500_goal` and `get_player_landing` let your ReAct agent compare active players against Hall of Fame trajectories. The agent grabs the historical list first. Then it queries the active roster using `suggest_active_players` to find current candidates. The output of one API call becomes the input for the next. Your agent pulls a team's schedule with `get_team_season_schedule`, extracts upcoming opponents, and runs `get_team_summary` on each to generate a weekly scouting report.

Aggregate advanced stats across the league

You pull deep analytics using `get_skater_powerplay` and `get_goalie_advanced` within a single execution cycle. The LangChain agent decides which stats matter based on the user's question. It queries the data, filters out the noise, and returns a clean summary of powerplay efficiency. Multi-server MCP aggregation means you can mix this hockey data with other APIs. Your agent pulls the latest standings via `get_current_standings`, formats the data, and writes it to a local database using a completely different tool in the same workflow.

Setup guide

Set up NHL MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NHL tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "nhl-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NHL transactions"
    })
    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 LangChain

Run `pip install langchain-mcp-adapters langgraph`. Initialize a `MultiServerMCPClient` with your endpoint URL, call `client.get_tools()`, and pass the array to your agent constructor.

Yes. LangSmith automatically traces every tool invocation. You see exactly how long `get_current_schedule` takes to return data and how many tokens the agent consumes processing the JSON.

Not by default. You need to use `client.session()` to maintain persistent context if your agent needs to reference a boxscore it pulled three turns ago.

The API returns an empty result or an error message. Your ReAct agent reads that failure, adjusts its strategy, and usually falls back to `suggest_players` to find the correct spelling.

The server only processes public sports data like boxscores, player biographies, and team schedules. Your Vinkius token secures the connection, and the V8 Isolate Sandbox destroys the execution environment the second your query finishes.

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