Sports Odds API
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sports Odds API Show me the live betting odds for the Lakers vs Celtics game tonight."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sports Odds API (BetRivers, Unibet & 22 more books)
Languages: English · 简体中文 · 日本語 · 한국어 · Español · Português (Brasil) · Deutsch · Français · Русский · Türkçe
Live odds from 24 Kambi-powered sportsbooks in one call — BetRivers (12 US states + Ontario), Unibet, Paf, Svenska Spel, ATG. One row per game with every book's price and the best price per outcome. Pay per call, no subscription.
Apify Store: https://apify.com/publicrecords/sports-odds-api
MCP server: https://mcp.apify.com?tools=publicrecords/sports-odds-api
MCP endpoint
https://mcp.apify.com?tools=publicrecords/sports-odds-apiTransport: Streamable HTTP (hosted by Apify, see https://docs.apify.com/mcp).
Related MCP server: mcp-odds-api
Auth
Sign in with Apify OAuth when your client prompts you, or send the header
Authorization: Bearer <APIFY_TOKEN> where <APIFY_TOKEN> is your own Apify API token.
Never commit a real token.
Client setup
Claude
Claude Code:
claude mcp add --transport http sports-odds "https://mcp.apify.com?tools=publicrecords/sports-odds-api"Claude Desktop / claude.ai: Settings → Connectors → Add custom connector, and paste the MCP endpoint URL above.
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"sports-odds": {
"url": "https://mcp.apify.com?tools=publicrecords/sports-odds-api"
}
}
}VS Code
.vscode/mcp.json:
{
"servers": {
"sports-odds": {
"type": "http",
"url": "https://mcp.apify.com?tools=publicrecords/sports-odds-api"
}
}
}To use a token instead of OAuth, add "headers": { "Authorization": "Bearer <APIFY_TOKEN>" } next to "url".
Disclosure: I maintain this Actor.
Local stdio server (open source)
This repo also ships a small MCP server in src/ for clients that only run local stdio servers. It answers initialize and tools/list locally from tools.json, which is generated from each Actor's public input schema and checked for drift in CI and weekly, so any client or directory can inspect the tools with no token. tools/call is forwarded to the hosted Apify MCP endpoint above with your own APIFY_TOKEN; without a token a call returns a clear error instead of running anything. The token is only sent in the Authorization header and is never logged.
{
"mcpServers": {
"sports-odds": {
"command": "npx",
"args": ["-y", "github:GeminiGeorge22/sports-odds-mcp"],
"env": { "APIFY_TOKEN": "YOUR_APIFY_TOKEN" }
}
}
}Or from a clone:
git clone https://github.com/GeminiGeorge22/sports-odds-mcp.git
cd sports-odds-mcp && npm install
APIFY_TOKEN=YOUR_APIFY_TOKEN node src/server.jsOptional env: APIFY_ACTORS (comma-separated subset of the Actors above) and APIFY_MCP_URL (full endpoint override).
Tests run against an in-memory mock server, with no network and no token: npm test. Requires Node.js 18+.
Python (uvx/pip)
A matching Python version of this server lives in python/, built on the official mcp Python SDK: same tools, same APIFY_TOKEN, same hosted endpoint. Requires Python 3.10+.
{
"mcpServers": {
"sports-odds": {
"command": "uvx",
"args": ["sports-odds-mcp"],
"env": { "APIFY_TOKEN": "YOUR_APIFY_TOKEN" }
}
}
}Or with pip: pip install sports-odds-mcp, then run sports-odds-mcp. Python tests: cd python && pip install -e ".[test]" && env -u APIFY_TOKEN python -m pytest.
See also
Awesome Sports Odds MCP: a curated list of sports odds MCP servers, one provider per sportsbook.
ecommerce-search-rankings-mcp: E-commerce search results and product rankings across Amazon, eBay, Walmart, Google Shopping, AliExpress, Shopify and Etsy.
ecommerce-sales-mcp: E-commerce sales signals: Amazon bestsellers and reviews, eBay sold prices, TikTok Shop and Etsy shop sales.
forecast-accuracy-mcp: Forecast accuracy and track records: forecasts vs actuals, earnings beats, prediction markets, archived pages and news.
sports-betting-stats-mcp: Sports betting odds and stats: sportsbook odds, player props, scores, xG, closing lines, horse racing.
etsy-sales-mcp: Etsy search results and Etsy shop sales counters.
ats-jobs-mcp: New job postings from Greenhouse, Lever, Ashby and SmartRecruiters.
gov-tenders-mcp: Government tenders, grants, awards and council meetings.
Available Tools
1 toolpublicrecords--sports-odds-apiSports Odds API: BetRivers, Unibet, Paf, Svenska Spel, ATGARead-onlyInspect
Sports Odds API: BetRivers, Unibet, Paf, Svenska Spel, ATG. Live odds from 24 Kambi-powered sportsbooks in one call: BetRivers (12 US states + Ontario), Unibet (7 countries), Paf, Svenska Spel and ATG. One row per game with every book's price and the best price per outcome.
When to use: Use when you need current pre-match or live prices for a game or league from Kambi-powered books (BetRivers, Unibet, Paf, Svenska Spel, ATG) and want to compare books or find the best price per outcome. Not for DraftKings/FanDuel or historical odds.
Returns: the run's dataset rows as structured JSON (one row per result), plus the run and dataset IDs for paging the full dataset.
Behavior: starts one run of the Apify Actor "publicrecords/sports-odds-api" through Apify's hosted MCP gateway (mcp.apify.com) with your own APIFY_TOKEN; the run uses your Apify account. Read-only: it only reads public web data and changes nothing on the source site. Docs: https://apify.com/publicrecords/sports-odds-api
Inputs: leagues, markets, maxEvents, operators, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong one. Its stated scope (current Kambi-book odds comparison, not DraftKings/FanDuel or historical data) is explicitly bounded, leaving no internal overlap to confuse an agent.
The name 'publicrecords--sports-odds-api' is a namespaced actor slug rather than a verb_noun action, which is readable but not a predictable tool convention. With a single tool there is no pattern to be consistent with, so it lands as mixed-but-legible.
A single tool is thin for a data-fetching server, but here it is a deliberate one-tool proxy for a whole Apify actor, so the scope isn't mismatched so much as shallow. It sits at the borderline of 'one tool feels thin.'
The core operation—get odds rows plus run/dataset IDs—is covered, but the description advertises paging the full dataset while exposing no tool to fetch subsequent pages or list supported sportsbooks/leagues/markets. Agents can get the first page but hit a dead end for anything beyond it.
Maintenance
Related MCP Connectors
Live odds, cross-book +EV and graded player-prop results across 37 books. Hosted endpoint included.
Sportsbook-derived no-vig fair value with confidence, provenance, and history over REST/MCP.
Live sports data: scores, play-by-play, box scores, odds and props. No key needed to start.
Live and prematch FanDuel odds, price drops and feed health. No key, no signup.
Related MCP Servers
AlicenseAqualityBmaintenanceLive and pre-match sports odds from 450+ bookmakers across 34 sports, plus Polymarket and Kalshi. Events, odds, fair prices, value bets, arbitrage, historical closing lines and bet settlement for AI assistants.331,129 npm2MIT- AlicenseNot gradedqualityCmaintenanceEnables fetching sportsbook odds, live scores, and event information across 70+ books and 30+ leagues, with tools to list sports, get scores, and discover events.108 npm1MIT
- FlicenseNot gradedqualityDmaintenanceProvides comprehensive sports intelligence including live scores, standings, schedules, betting odds, news, highlights, and more via SSE transport.-
- AlicenseAqualityBmaintenanceEnables MCP-compatible clients to access sports betting odds, player props, prediction markets, live previews, coverage checks, and ParlayAPI account signup through native tools.221MIT