odds-api-mcp-server
LocalAbout odds-api-mcp-server
odds-api-mcp-server gives AI clients access to Odds-API.io sports odds and betting analytics. It covers live and historical data across sports, events, and bookmakers.
Key features
- 01Sports, leagues, and event lookup
- 02Live, multi-event, and historical odds
- 03Odds movement tracking
- 04Value bet and arbitrage discovery
- 05Bet grading and settlement data
- 06API documentation resources
Use cases
- 01Compare odds for upcoming events
- 02Review historical lines and results
- 03Identify positive-EV or arbitrage opportunities
- 04Track sharp bookmaker line movements
MCP support
The MCP server exposes Odds-API.io v3 tools and documentation resources to MCP clients. An Odds-API.io API key is required.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y odds-api-mcp-serverODDS_API_KEYSecretOdds-API.io API key (free tier available, no credit card)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
22Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEOdds-API.io MCP Server
Model Context Protocol (MCP) server for Odds-API.io - providing AI tools like Claude, Cursor, and VS Code with direct access to sports betting odds data.
Full AI-tooling docs: docs.odds-api.io/ai-vibe-coding
Features
- 25 API tools covering the full Odds-API.io v3 surface: sports, events, odds, historical data, bet settlement, value bets, arbitrage, dropping odds, and more
- Documentation resources for AI context
- Real-time data from 450+ bookmakers across 34 sports
Quick Start
One-Click Install (Claude Desktop)
Download the latest .mcpb file from Releases and open it. Claude Desktop will prompt you for your API key.
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 your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"odds-api": {
"command": "npx",
"args": ["-y", "odds-api-mcp-server"],
"env": {
"ODDS_API_KEY": "your-api-key"
}
}
}
}
Cursor
Add to your Cursor MCP settings (.cursor/mcp.json in your project or global config):
{
"mcpServers": {
"odds-api": {
"command": "npx",
"args": ["-y", "odds-api-mcp-server"],
"env": {
"ODDS_API_KEY": "your-api-key"
}
}
}
}
VS Code
Add to your VS Code settings (.vscode/mcp.json):
{
"servers": {
"odds-api": {
"command": "npx",
"args": ["-y", "odds-api-mcp-server"],
"env": {
"ODDS_API_KEY": "your-api-key"
}
}
}
}
Global Install (alternative)
npm install -g odds-api-mcp-server
Then use odds-api-mcp as the command instead of npx -y odds-api-mcp-server.
Configuration
| Variable | Required | Description |
|---|---|---|
ODDS_API_KEY | Yes | Your API key from odds-api.io |
Available Tools
Sports & Leagues
| Tool | Description |
|---|---|
get_sports | List all available sports with slugs |
get_leagues | Get leagues for a sport (with optional all flag for inactive leagues) |
get_markets | List the exact market names a sport serves, with shape, period and prematch/live availability |
Bookmakers
| Tool | Description |
|---|---|
get_bookmakers | List all supported bookmakers |
get_selected_bookmakers | Get your currently selected bookmakers |
select_bookmakers | Add bookmakers to your selection |
clear_selected_bookmakers | Clear all selected bookmakers (once per 12h) |
Events
| Tool | Description |
|---|---|
get_events | Get events with filtering (league, status, date range, participant, bookmaker, pagination) |
get_event | Get a single event by ID |
get_live_events | Get currently live events |
search_events | Search events by team name or text |
Odds
| Tool | Description |
|---|---|
get_odds | Get odds for an event from selected bookmakers |
get_multi_odds | Get odds for up to 10 events in one call |
get_odds_movements | Get historical line movements for a market |
get_updated_odds | Get recently changed odds (polling), for the markets you name |
Historical
| Tool | Description |
|---|---|
get_historical_events | Get finished events for a sport/league/date range |
get_historical_odds | Get closing odds and scores for finished events |
Betting Analytics
| Tool | Description |
|---|---|
get_settlements | Status, final score and final flag for up to 50 events |
grade_bets | Settle up to 50 bets as won, lost, void, half won or half lost |
get_value_bets | Get positive EV opportunities for a bookmaker |
get_arbitrage_bets | Get arbitrage opportunities with optimal stakes |
get_dropping_odds | Track sharp bookmaker line movements by sport, league, market, and time window |
Participants
| Tool | Description |
|---|---|
get_participants | Get teams/participants for a sport |
get_participant | Get a single participant by ID |
Reference
| Tool | Description |
|---|---|
get_documentation | Fetch full API documentation |
Resources
| Resource URI | Description |
|---|---|
odds-api://documentation | Complete API documentation |
odds-api://openapi | OpenAPI/Swagger specification |
Example Usage
Once configured, ask your AI assistant things like:
- "What sports are available on Odds-API?"
- "Show me upcoming Premier League matches"
- "Get odds for the next Arsenal match from Bet365 and SingBet"
- "Find value bets on Bet365 with event details"
- "Are there any arbitrage opportunities between Bet365 and Unibet?"
- "Show me how the odds moved for event 12345 on the spread market"
- "Get historical results for La Liga in January 2026"
- "Show me the biggest dropping odds in football right now"
- "What Premier League odds have dropped the most in the last 12 hours?"
Development
git clone https://github.com/odds-api-io/odds-api-mcp-server
cd odds-api-mcp-server
npm install
npm run build
npm test
License
MIT
Links
- Odds-API.io - Main website
- Documentation - API docs
- API Reference - Swagger/OpenAPI
- npm - Package registry
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.