How to Use the GameScorekeeper MCP in AutoGen

Q: How do I give GameScorekeeper tools to my AutoGen agents?

You use the mcpservertools function to get the list of tools from the GameScorekeeper MCP Server. Then you pass that tool list directly to your AssistantAgent during initialization.

Q: What's a good agent setup for GameScorekeeper with AutoGen?

A solid setup is a three-agent group: a UserProxyAgent to take the request, a "DataFetcher" agent with all the GameScorekeeper tools, and a "Summarizer" agent with no tools that just interprets the data the fetcher provides.

Let your AutoGen agents debate sports outcomes. Use live data to fuel conversations about lineups, team form, and match predictions.

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 AutoGen

Create your Vinkius account to connect GameScorekeeper 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 GameScorekeeper with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel Agent Debates with Live Data

Give your agents something to argue about. One agent can act as an optimist, using `get_team_form` to highlight a team's recent wins. A second, more skeptical agent can use `get_fixture_lineup` to point out that the star player is on the bench. This is how AutoGen finds better answers. The agents converse, challenge each other's findings, and use data from GameScorekeeper tools to back up their arguments. The final output is a result of that debate, not a single-shot query.

Create Specialist Sports Agents

Build a team of agents with different roles. A "StatsAgent" can be given access to just `get_player_stats`. A "SchedulerAgent" can only use `list_fixtures` and `list_competitions`. They have to work together to answer complex questions. This multi-agent approach lets you model real-world analysis. Your agents can replicate a sports newsroom, with one fetching raw data, another interpreting it, and a manager synthesizing their findings. This MCP Server provides the tools for each specialist.

Simulate Game Scenarios with AutoGen

Set up a conversation to predict a match outcome. One agent pulls the lineup with `get_fixture_lineup`, another gets team details with `get_team_details`, and a third analyzes recent performance with `get_team_form`. They then debate the likely winner. Because AutoGen agents can correct each other, you can catch bad assumptions. If an agent overstates a team's strength, another can counter with data from `get_player_stats` for their key striker, leading to a more nuanced conclusion.

Setup guide

Set up GameScorekeeper 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 GameScorekeeper 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="GameScorekeeper_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent GameScorekeeper 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="GameScorekeeper_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent GameScorekeeper 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 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 AutoGen

You use the `mcp_server_tools` function to get the list of tools from the GameScorekeeper MCP Server. Then you pass that tool list directly to your `AssistantAgent` during initialization.

Yes. You can create multiple tool lists from the MCP server and assign them to different agents. For example, give your "LineupChecker" agent only the `get_fixture_lineup` tool to keep its role focused.

A solid setup is a three-agent group: a `UserProxyAgent` to take the request, a "DataFetcher" agent with all the GameScorekeeper tools, and a "Summarizer" agent with no tools that just interprets the data the fetcher provides.

The agents decide based on the conversation context and their instructions. If one agent asks "What was the score?", another agent might recognize that `get_fixture_details` is the right tool for the job and execute it.

All queries for sports data, like team details or player profiles, are proxied through Vinkius's secure infrastructure. The connection is encrypted, and the computing environment for each request is temporary and destroyed after use, ensuring none of your query history is retained.

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