SDKs & Libraries

Use our official SDKs to integrate Odds-API.io into your project in minutes. Each SDK wraps the full REST API with type safety, error handling, and built-in best practices.

Official SDKs

Python SDK

Full-featured Python client with sync and async support. Available on PyPI.

Node.js SDK

TypeScript-first SDK with full type definitions. Works with ESM and CommonJS.

MCP Server

Model Context Protocol server for AI tools like Claude, Cursor, and VS Code.

Python

Install the SDK:

pip install odds-api-io

Quick Start

from odds_api import OddsAPIClient

client = OddsAPIClient(api_key="YOUR_API_KEY")

# Get all sports
sports = client.get_sports()

# Get Premier League events
events = client.get_events(sport="football", league="england-premier-league")

# Get odds from multiple bookmakers
odds = client.get_event_odds(
    event_id=events[0]['id'],
    bookmakers="Bet365,SingBet,FanDuel"
)

# Display odds with direct bet links
for bookie, markets in odds['bookmakers'].items():
    ml = next((m for m in markets if m['name'] == 'ML'), None)
    if ml:
        o = ml['odds'][0]
        print(f"{bookie}: H {o['home']} | D {o['draw']} | A {o['away']}")

# Direct bet links
for bookie, url in odds.get('urls', {}).items():
    print(f"  Bet at {bookie}: {url}")

Async Support

import asyncio
from odds_api import AsyncOddsAPIClient

async def main():
    async with AsyncOddsAPIClient(api_key="YOUR_API_KEY") as client:
        sports = await client.get_sports()
        events = await client.get_events(sport="basketball", league="usa-nba")
        print(f"Found {len(events)} NBA events")

asyncio.run(main())

Find Value Bets

value_bets = client.get_value_bets(
    bookmaker="Bet365",
    include_event_details=True
)

for bet in sorted(value_bets, key=lambda x: x['expectedValue'], reverse=True)[:5]:
    ev = bet['expectedValue'] - 100
    print(f"+{ev:.1f}% EV | {bet['market']['name']} | {bet['betSide']} @ {bet['bookmakerOdds'][bet['betSide']]}")
    print(f"  Bet link: {bet['bookmakerOdds'].get('href', 'N/A')}")

View on GitHub

Full documentation, examples, and API reference.

Node.js / TypeScript

Install the SDK:

npm install odds-api-io

Quick Start (TypeScript)

import { OddsAPIClient } from 'odds-api-io';

const client = new OddsAPIClient({ apiKey: 'YOUR_API_KEY' });

// Get all sports
const sports = await client.getSports();

// Get Premier League events
const events = await client.getEvents({
  sport: 'football',
  league: 'england-premier-league',
});

// Get odds from multiple bookmakers
const odds = await client.getEventOdds({
  eventId: events[0].id,
  bookmakers: 'Bet365,SingBet,FanDuel',
});

// Display odds with direct bet links
for (const [bookie, markets] of Object.entries(odds.bookmakers)) {
  const ml = markets.find(m => m.name === 'ML');
  if (ml?.odds?.[0]) {
    const o = ml.odds[0];
    console.log(`${bookie}: H ${o.home} | D ${o.draw} | A ${o.away}`);
  }
}

// Direct bet links
for (const [bookie, url] of Object.entries(odds.urls || {})) {
  console.log(`  Bet at ${bookie}: ${url}`);
}

Quick Start (JavaScript)

const { OddsAPIClient } = require('odds-api-io');

const client = new OddsAPIClient({ apiKey: 'YOUR_API_KEY' });

const sports = await client.getSports();
console.log(`Found ${sports.length} sports`);

Find Arbitrage Opportunities

const arbs = await client.getArbitrageBets({
  bookmakers: 'Bet365,SingBet',
  limit: 10,
  includeEventDetails: true,
});

arbs.forEach(arb => {
  console.log(`${arb.profitMargin.toFixed(2)}% margin`);
  arb.legs.forEach(leg => {
    console.log(`  ${leg.bookmaker} | ${leg.side} @ ${leg.odds}`);
  });
});

View on GitHub

Full documentation, examples, and API reference.

MCP Server (AI Tools)

Use Odds-API.io directly from AI coding tools like Claude, Cursor, and VS Code. The MCP server page has setup for every client, example prompts and all 25 tools.

Claude Code CLI

claude mcp add odds-api --env ODDS_API_KEY="your-api-key" -- npx -y odds-api-mcp-server

Claude Desktop

Add to claude_desktop_config.json (~/Library/Application Support/Claude/ on macOS, %APPDATA%\Claude\ on Windows):

{
  "mcpServers": {
    "odds-api": {
      "command": "npx",
      "args": ["-y", "odds-api-mcp-server"],
      "env": {
        "ODDS_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

Add to your MCP settings:

{
  "mcpServers": {
    "odds-api": {
      "command": "npx",
      "args": ["-y", "odds-api-mcp-server"],
      "env": {
        "ODDS_API_KEY": "your-api-key"
      }
    }
  }
}

Once configured, ask your AI assistant things like:

“Get me upcoming Premier League matches with odds”
“Find value bets from Bet365”
“Show arbitrage opportunities”

View on GitHub

Installation guide and available tools.

Error Handling

All SDKs include custom error classes for clean error handling:

from odds_api import (
    OddsAPIClient,
    InvalidAPIKeyError,
    RateLimitExceededError,
    NotFoundError,
)

try:
    events = client.get_events(sport="basketball")
except InvalidAPIKeyError:
    print("Invalid API key")
except RateLimitExceededError:
    print("Rate limit exceeded - wait before retrying")
except NotFoundError:
    print("Resource not found")

import {
  OddsAPIClient,
  InvalidAPIKeyError,
  RateLimitExceededError,
  NotFoundError,
} from 'odds-api-io';

try {
  const events = await client.getEvents({ sport: 'basketball' });
} catch (error) {
  if (error instanceof InvalidAPIKeyError) {
    console.error('Invalid API key');
  } else if (error instanceof RateLimitExceededError) {
    console.error('Rate limit exceeded');
  } else if (error instanceof NotFoundError) {
    console.error('Not found');
  }
}

WebSocket + SDK

Combine REST SDKs with WebSocket for a complete solution. Pre-fetch all odds via REST, then switch to WebSocket for real-time updates:

from odds_api import OddsAPIClient
import asyncio, json, websockets

# Step 1: Initial snapshot via REST SDK
client = OddsAPIClient(api_key="YOUR_API_KEY")
events = client.get_events(sport="football", league="england-premier-league")

odds_store = {}
for event in events:
    odds = client.get_event_odds(event_id=event['id'], bookmakers="Bet365,SingBet")
    odds_store[str(event['id'])] = odds.get('bookmakers', {})

print(f"Loaded {len(odds_store)} events via REST")

# Step 2: Connect to WebSocket for live updates (websockets compresses by default, which is required)
async def stream():
    url = "wss://api.odds-api.io/v3/ws?apiKey=YOUR_API_KEY&markets=ML,Spread,Totals&sport=football"
    async with websockets.connect(url, ping_interval=30) as ws:
        async for message in ws:
            data = json.loads(message)
            if data['type'] == 'updated':
                odds_store[data['id']] = {data['bookie']: data['markets']}
                print(f"Updated: Event {data['id']} | {data['bookie']}")

asyncio.run(stream())

See the full WebSocket + prefetch examples in the Python SDK and Node.js SDK repos.

All Repositories

Repository	Type	Install	Links
odds-api-python	Python SDK	`pip install odds-api-io`	PyPI
odds-api-node	Node.js SDK	`npm install odds-api-io`	npm
odds-api-mcp-server	MCP Server	`npx odds-api-mcp-server`	npm

Need an SDK in another language? Let us know at hello@odds-api.io

Getting Started

Guides

Examples

Official SDKs

Python SDK

Node.js SDK

MCP Server

Python

Quick Start

Async Support

Find Value Bets

View on GitHub

Node.js / TypeScript

Quick Start (TypeScript)

Quick Start (JavaScript)

Find Arbitrage Opportunities

View on GitHub

MCP Server (AI Tools)

Claude Code CLI

Claude Desktop

Cursor

View on GitHub

Error Handling

WebSocket + SDK

All Repositories

​Official SDKs

Python SDK

Node.js SDK

MCP Server

​Python

​Quick Start

​Async Support

​Find Value Bets

View on GitHub

​Node.js / TypeScript

​Quick Start (TypeScript)

​Quick Start (JavaScript)

​Find Arbitrage Opportunities

View on GitHub

​MCP Server (AI Tools)

​Claude Code CLI

​Claude Desktop

​Cursor

View on GitHub

​Error Handling

​WebSocket + SDK

​All Repositories

Official SDKs

Python

Quick Start

Async Support

Find Value Bets

Node.js / TypeScript

Quick Start (TypeScript)

Quick Start (JavaScript)

Find Arbitrage Opportunities

MCP Server (AI Tools)

Claude Code CLI

Claude Desktop

Cursor

Error Handling

WebSocket + SDK

All Repositories