How to Use the The Odds API MCP in AutoGen

Q: Can AutoGen handle different types of market data from The Odds API?

Absolutely. You can assign specific tools—like getodds for betting lines and listsports for categorization—to different agents, forcing them to cross-reference the information.

Force consensus on sports insights using AutoGen's multi-agent debate framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect The Odds API MCP to AutoGen

Create your Vinkius account to connect The Odds API to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup The Odds API with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Deliberative Odds Analysis with the MCP Server

You set up three agents: one for odds, one for scores, and one for sports lists. The 'odds' agent uses `get_odds` to predict a probability. Then, it forces the 'scores' agent to debate that prediction using real-time data from `get_scores`. This negotiation leads to a consensus decision.

Debating Market Feasibility

The agents can use `list_sports` to establish the scope of available markets. The 'security' agent might flag that certain sports are too volatile for prediction, while the 'performance' agent insists on running the model anyway. This debate ensures all variables are considered.

Consensus-Driven Data Retrieval

Instead of one tool call, you get a reasoned outcome. The agents discuss whether `get_odds` is sufficient or if they need to run it multiple times for different sports listed by `list_sports`. This makes the final conclusion much more defensible.

Setup guide

Set up The Odds API 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 The Odds API 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="The Odds API_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent The Odds API 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="The Odds API_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent The Odds API 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 The Odds API. 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 The Odds API 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 The Odds API MCP in AutoGen

The agents assign roles. One agent might be tasked with gathering data using `get_odds`, and another challenges that raw output by comparing it to scores retrieved via `get_scores`. They argue until they find a consensus.

Absolutely. You can assign specific tools—like `get_odds` for betting lines and `list_sports` for categorization—to different agents, forcing them to cross-reference the information.

The MCP tool adapter handles schema conversion automatically. You just pass `get_odds()` results into the conversation, and the agents treat it like any piece of shared conversational context.

The system is built to challenge assumptions. If one agent gets a single odds result, another can use `get_scores` to validate if that outcome makes sense based on recent play.

It handles real-time odds and scores. The agents process these structured betting statistics, keeping the focus strictly on market data analysis.

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