How to integrate College football data MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
College football data Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting College football data to AutoGen using the Composio tool router. By the end, you'll have a working College football data agent that can show betting lines for this week's games, get tv schedule for sec games this weekend, list advanced box scores for ohio state, summarize team talent rankings for 2024 through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a College football data account through Composio's College football data MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for College football data
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call College football data tools
  • Run a live chat loop where you ask the agent to perform College football data operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the College football data MCP server, and what's possible with it?

The College football data MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your College Football Data account. It provides structured and secure access to comprehensive college football stats, schedules, advanced analytics, and recruiting data, so your agent can fetch game results, analyze team performance, retrieve broadcast info, and explore historical metrics on your behalf.

  • Retrieve game schedules and results: Instantly fetch upcoming games, past scores, and matchup outcomes filtered by season, week, team, or conference.
  • Analyze advanced team and player stats: Have your agent pull in-depth box scores, advanced metrics, and season-long analytics to compare team or player performance.
  • Access media and broadcast information: Quickly get details on TV, radio, and streaming coverage for selected games, including broadcast schedules and platforms.
  • Review team talent and recruiting rankings: Let your agent track composite team talent scores and recruiting class data across seasons for any program.
  • Explore historical conference and division data: Effortlessly trace a team's conference membership history, division alignment, and related metadata over time.

Supported Tools & Triggers

Tools
Advanced Box ScoreTool to retrieve advanced box score metrics for a single college football game.
Advanced Game StatsTool to retrieve advanced team metrics at the game level.
Advanced Season Stats by TeamTool to retrieve advanced season metrics aggregated by team and season.
Betting LinesTool to fetch betting lines and totals by game and provider.
Composite Team TalentTool to fetch composite team talent rankings by season.
Conference Memberships HistoryTool to retrieve historical conference memberships for teams, including years active and division.
Divisions by ConferenceTool to list FBS/FCS conference divisions with active years and metadata.
Get Drive DataTool to retrieve drive-level data and results.
Get Game MediaTool to retrieve game media information and broadcast schedules (TV, radio, web, etc.
Get Games and ResultsTool to retrieve games and results for a given season/week/team.
Get Player Game StatsTool to fetch player statistics at the game level.
Get Team Game StatsTool to fetch team statistics at the game level.
List Coaches and HistoryTool to get coaching records and history.
List ConferencesTool to list all college football conferences.
List FBS TeamsTool to list FBS teams for a given season.
List FCS TeamsTool to list FCS teams for a given season and conference.
List TeamsTool to list college football teams.
List Venues and StadiumsTool to list college football venues with metadata (name, capacity, location, etc.
NFL Draft PicksTool to list NFL Draft picks.
NFL Draft PositionsTool to list NFL draft positions.
NFL Draft TeamsTool to list NFL teams used in draft endpoints.
Play-by-Play DataTool to fetch play-by-play data for college football games.
Play Stats PlayerTool to fetch player-level stats tied to individual plays.
Play Stat TypesTool to fetch all play-level stat type definitions.
Player PPA by GameTool to retrieve player-level PPA/EPA broken down by game.
PPA Player By SeasonTool to fetch player-level PPA/EPA aggregated by season.
Predict Expected Points (EP)Tool to get expected points by down, distance, and field position.
PPA Team By GameTool to retrieve team Predicted Points Added (PPA) by game.
Rankings PollsTool to retrieve weekly human/computer poll rankings.
Elo RatingsTool to retrieve Elo ratings for college football teams.
SP+ RatingsTool to retrieve SP+ team ratings.
SRS RatingsTool to retrieve Simple Rating System (SRS) team ratings.
Recruiting Group DictionaryTool to list recruiting position group aggregations.
Recruiting Transfer PortalTool to retrieve transfer portal entries for a given season.
Returning Production by TeamTool to fetch Bill Connelly–style returning production splits by team and season.
Season Stats PlayerTool to fetch basic season stats aggregated by player and season.
Season Team StatsTool to get basic season stats aggregated by team and season.
Season Types DictionaryTool to list season types.
Team Matchup HistoryTool to retrieve head-to-head team matchup records over a date range.
Team season recordsTool to fetch team season records by year with optional filters.
Get Team RosterTool to fetch roster for a given team and season.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A College football data account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to College football data via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's College football data connections to use

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

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

load_dotenv()

async def main():
    # Initialize Composio and create a College football data session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["college_football_data"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes College football data tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create College football data assistant agent with MCP tools
    agent = AssistantAgent(
        name="college_football_data_assistant",
        description="An AI assistant that helps with College football data operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the College football data tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any College football data related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which College football data tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with College football data and AutoGen:

import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

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

load_dotenv()

async def main():
    # Initialize Composio and create a College football data session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["college_football_data"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create College football data assistant agent with MCP tools
        agent = AssistantAgent(
            name="college_football_data_assistant",
            description="An AI assistant that helps with College football data operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any College football data related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into College football data through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for College football data, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build College football data MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use College football data MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use College football data MCP with Claude Agent SDK

Google ADK

Google ADK

Use College football data MCP with Google ADK

LangChain

LangChain

Use College football data MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use College football data MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use College football data MCP with Mastra AI

LlamaIndex

LlamaIndex

Use College football data MCP with LlamaIndex

CrewAI

CrewAI

Use College football data MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and College football data MCP?

With a standalone College football data MCP server, the agents and LLMs can only access a fixed set of College football data tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from College football data and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right College football data tools.

Can I manage the permissions and scopes for College football data while using Tool Router?

Yes, absolutely. You can configure which College football data scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your College football data data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free