How to Use the GameScorekeeper MCP in OpenAI Agents SDK

Q: How do I initialize GameScorekeeper in the OpenAI Agents SDK?

You install openai-agents via pip. Then you create an MCPServerStreamableHttp object with your endpoint URL and pass it to the mcpservers array in your Agent constructor.

Q: Can the OpenAI Agents SDK hand off GameScorekeeper tasks to other agents?

Yes. You can have a dedicated agent pulling data with getteamdetails and then routing that context to a separate analysis agent. The built-in handoff mechanism manages the state transfer.

Connect GameScorekeeper to your OpenAI Agents SDK to pull live sports data directly into production agent systems.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GameScorekeeper MCP to OpenAI Agents SDK

Create your Vinkius account to connect GameScorekeeper 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 GameScorekeeper with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live sports agents with this MCP Server

GameScorekeeper gives your OpenAI agent direct access to sports data via tools like `list_fixtures` and `get_fixture_details`. You configure the endpoint in your Python script, pass it to the agent constructor, and the model auto-discovers the available endpoints. When you need to build an agent that tracks live matches, you just let the SDK handle the routing. If an end user asks for current scores, the agent calls the API, parses the JSON, and hands off the structured data to a specialized sports-reporting agent using the framework's built-in routing.

Pull player stats and team form

The `get_player_stats` and `get_team_form` tools return historical performance metrics straight to your Python runtime. Your agent grabs the raw numbers and uses OpenAI's guardrails to validate the output before pushing it to a frontend dashboard. You don't have to write custom polling loops. The agent decides when to fetch new data based on user prompts. It pulls the lineup with `get_fixture_lineup`, checks the player histories, and formats the response while the dashboard tracks the execution trace.

Map entire tournament structures

Use `list_competitions` and `list_competition_stages` to map out massive esports tournaments. The agent retrieves the bracket data and stores it in memory for the duration of the session. Since the OpenAI Agents SDK supports caching, setting `cacheToolsList=True` keeps your latency low. The agent only fetches the tournament tree once, then spends its token budget analyzing the actual matchups instead of constantly hitting the schema endpoint.

Setup guide

Set up GameScorekeeper 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 GameScorekeeper tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GameScorekeeper 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="GameScorekeeper Agent",
            instructions="You have access to GameScorekeeper 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 GameScorekeeper. 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 GameScorekeeper 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 GameScorekeeper MCP in OpenAI Agents SDK

You install `openai-agents` via pip. Then you create an `MCPServerStreamableHttp` object with your endpoint URL and pass it to the `mcp_servers` array in your Agent constructor.

Yes. You can have a dedicated agent pulling data with `get_team_details` and then routing that context to a separate analysis agent. The built-in handoff mechanism manages the state transfer.

It does. You define constraints in your agent setup. If a tool like `get_player_details` returns an unexpected string, the guardrail catches it before the agent acts on the data.

Rely on the framework's tracing to monitor your request volume. You can write custom logic to throttle how often the agent calls `get_fixture_details` during a live match.

This integration handles public esports and football statistics, team rosters, and match schedules. The server only reads external sports databases and never accesses your internal user records or proprietary codebase.

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