How to Use the API-Football MCP in OpenAI Agents SDK

Q: Can I build multi-agent handoffs using API-Football and OpenAI Agents SDK?

You can. Designate one agent to fetch matches with getfixtures and have it hand off the raw data to a specialized analysis agent for processing.

Q: How do I search for specific teams using this setup?

Your agent will call searchfootballteams automatically when you ask about a specific club. It matches the query against the database and returns the correct team ID.

Build production-ready soccer bots with OpenAI Agents SDK and real-time football data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect API-Football MCP to OpenAI Agents SDK

Create your Vinkius account to connect API-Football 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 API-Football with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Match Monitors with OpenAI Agents SDK

The API-Football MCP Server lets your agent monitor live games as they happen. By calling `list_live_fixtures`, your agent pulls current match events, scores, and updates without you writing custom API wrappers. The SDK runs this MCP tool inside an async context manager. You pass the server to the agent constructor, and the agent auto-discovers how to query real-time data on the fly.

Audit Player Stats via MCP Server

The API-Football MCP Server delivers deep player metrics directly inside your agentic loops. Your agent uses `get_player_info` and `get_league_topscorers` to pull exact stats, goals, and history for any player in the database. In production, you can set up specialized agents that hand off tasks to each other. One agent fetches the raw data, while another handles the analysis, all monitored through your OpenAI dashboard.

Analyze League Tables Instantly

The API-Football MCP Server keeps your database updated with current league tables using `get_standings` and `list_leagues`. Your agent polls these tools to rebuild standings tables and flag sudden position shifts. To keep latency low, configure the SDK with cacheToolsList=True. This stops the agent from repeatedly querying the server schema, speeding up response times when analyzing large leagues.

Setup guide

Set up API-Football 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 API-Football tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip, then initialize the server using MCPServerStreamableHttp with your endpoint URL. Pass this server instance in the mcp_servers list when constructing your agent.

Yes. You can set cacheToolsList=True in your server parameters to prevent the SDK from fetching the tool definitions on every single run, which cuts down network overhead.

You can. Designate one agent to fetch matches with `get_fixtures` and have it hand off the raw data to a specialized analysis agent for processing.

Your agent will call `search_football_teams` automatically when you ask about a specific club. It matches the query against the database and returns the correct team ID.

The server only processes football match fixtures, team stats, and league standings. Your queries run through an ephemeral V8 sandbox, meaning no soccer data or API keys are stored on our servers after the execution ends.

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