How to Use the The Odds API MCP in Mastra AI

Q: Can I sequence calls to list sports and then get odds using Mastra AI?

Yes. You can build a clear workflow: use listsports first to validate the sport ID, and then pass that validated ID into getodds. It's sequential and reliable.

Q: Is The Odds API suitable for complex event analysis in Mastra AI?

Yep. You can build multi-step processes: check scores with getscores, decide if a high-stakes odds check is needed, and then execute getodds only if necessary.

Q: If I need to check multiple sports, what is the best way with The Odds API in Mastra AI?

Run listsports first. Then loop through the results, calling getodds for each one within your workflow. This keeps everything organized and fault-tolerant.

Build reliable, multi-step workflows with Mastra AI on 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 Mastra AI

Create your Vinkius account to connect The Odds API to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated Odds Analysis Flow

You can set up a complex workflow that first calls `list_sports` to determine the market. Next, it runs `get_odds` for several key matches. If one data source fails, Mastra AI automatically retries the odds fetch using another defined method. This means your agent doesn't halt when things get messy. It keeps running until it gets a valid set of betting lines from The Odds API, making your deployment reliable.

Conditional Scoring Check

Build logic that checks scores before making decisions. A workflow can first call `get_scores`. If the score difference is less than three points, it triggers a secondary action to fetch more detailed odds via `get_odds`. This conditional branching capability means you’re not just running tools; you're building actual decision trees that handle varying game states.

Robust Data Retrieval from MCP Server

The Mastra AI framework ensures data integrity when dealing with The Odds API. You can map out a sequence: 1) list available sports, then 2) get scores for the top three, and finally 3) fetch odds for those specific games. If any step fails, like if an endpoint is temporarily down, the built-in exponential backoff handles the retry cycle. You don't have to code that failure handling yourself.

Setup guide

Set up The Odds API MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All The Odds API tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "the-odds-api-mcp-client",
  servers: {
    "the-odds-api-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "The Odds API Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to The Odds API tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent The Odds API transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI includes automatic retries with exponential backoff built in. If the odds request fails, it waits and tries again automatically, so your workflow stays up.

Yes. You can build a clear workflow: use `list_sports` first to validate the sport ID, and then pass that validated ID into `get_odds`. It's sequential and reliable.

Yep. You can build multi-step processes: check scores with `get_scores`, decide if a high-stakes odds check is needed, and then execute `get_odds` only if necessary.

The server touches public sporting event data: sport names, league IDs, scores, and numerical odds. It's purely analytical data.

Run `list_sports` first. Then loop through the results, calling `get_odds` for each one within your workflow. This keeps everything organized and fault-tolerant.

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