How to Use the The Odds API MCP in CrewAI

Q: Is The Odds API good for multi-stage analysis in CrewAI?

Yes. You can mandate a sequence: Agent 1 gets scores using getscores, then Agent 2 uses the result to determine which specific odds need checking with getodds.

Q: Does The Odds API support all sport listings for CrewAI?

The listsports tool ensures that your agent has a full catalog of available sports. This prevents the crew from missing potential data sources when running against the MCP Server.

Build autonomous operations with CrewAI using The Odds API.

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 CrewAI

Create your Vinkius account to connect The Odds API to CrewAI — 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Specialized Research into Betting Lines

Assign a 'Research Agent' to use `list_sports` first. This agent gathers all possible markets, handing the list off to an 'Analysis Agent.' The Analysis Agent then uses `get_odds` on specific sports you target. This role-based setup means one agent handles data discovery while another focuses purely on comparing and weighing odds from The Odds API's output.

Collaborative Score Tracking

You can set up a 'Scoring Agent' that uses `get_scores` to pull the current state of play. Then, an 'Action Agent' takes over. The Action Agent doesn't just report scores—it compares them against historical data and reports discrepancies. This shared memory approach lets the agents build on each other’s findings, making complex sports analysis much more structured.

Autonomous Odds Comparison via MCP Server

The CrewAI framework allows you to run an entire operation that checks market viability. One agent uses `list_sports` for context; a second agent then runs `get_odds`. The whole system monitors and reports on discrepancies across multiple calls. This multi-agent setup is perfect when your goal isn't just data retrieval, but comparative analysis based on the results from this MCP Server.

Setup guide

Set up The Odds API MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke The Odds API tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="The Odds API Analyst",
    goal="Access and analyze The Odds API data via MCP.",
    backstory="Expert analyst with direct The Odds API access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent The Odds API transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="The Odds API Analyst",
        goal="Access and analyze The Odds API data via MCP.",
        backstory="Expert analyst with direct The Odds API access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent The Odds API transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign roles: one agent researches which sports to check via `list_sports`, and another analyzes the results by calling `get_odds` with those IDs. They pass context back and forth.

Yes. You can mandate a sequence: Agent 1 gets scores using `get_scores`, then Agent 2 uses the result to determine which specific odds need checking with `get_odds`.

The `list_sports` tool ensures that your agent has a full catalog of available sports. This prevents the crew from missing potential data sources when running against the MCP Server.

This server handles public, non-personal sporting event metrics: sport names, scores, and odds. No private user data is involved when using this MCP Server.

The 'Moderator Agent' can take the output from a previous agent (like a list of top-scoring sports) and dynamically feed those parameters into `get_odds` for the next step.

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