betbetter-mcp
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., "@betbetter-mcp What are the predicted odds for the Lakers 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.
betbetter-mcp
An MCP server that gives any AI assistant access to sports model win probabilities and fair odds across nine sports — no API key, no sign-up, free to use.
Data comes from the Bet Better open model API, published under CC BY 4.0.
What it gives you
For every upcoming fixture the model rates, you get:
Field | Meaning |
| The fixture, |
| Scheduled start, UTC |
| Head to Head, Spread, Total Points, player props… |
| The team, player or outcome being rated |
| Estimated chance it lands, 0–100 |
| Decimal odds implied by that probability |
|
|
| A one-sentence plain-English summary |
Leagues: AFL · MLB · NBA · NFL · NHL · NCAAF · UFC · WNBA · WTA tennis · EPL · La Liga · Serie A · Bundesliga · Ligue 1 · World Cup.
Related MCP server: Odds-API MCP Server
Install
npx betbetter-mcpClaude Desktop / Claude Code
Add to your MCP config:
{
"mcpServers": {
"betbetter": {
"command": "npx",
"args": ["-y", "betbetter-mcp"]
}
}
}Tools
Tool | What it does |
| Lists every league slug and feed type available |
| Rated selections for one league, filterable by minimum probability |
| Searches every league for a team or player and returns their rated selections |
Example
"What does the model think about the Geelong game this weekend?"
{
"game": "Geelong Cats @ Collingwood Magpies",
"market": "Head to Head",
"selection": "Geelong Cats",
"modelProbabilityPct": 54.9,
"fairOdds": 1.82,
"confidence": "LEAN"
}What this does not do
It publishes no bookmaker prices. There is no bookmaker name, market price or implied probability anywhere in the feed, and none is planned — the underlying odds data is licensed under terms that allow publishing derived work but not redistributing the feed. Everything here is the model's own output, so it cannot tell you where to bet or at what price.
Configuration
Variable | Default | Purpose |
|
| Override the API origin (testing) |
Responses are cached upstream for 15 minutes. Feeds are empty out of season — that is expected, not an error.
Responsible gambling
18+. Gambling involves risk and most people lose money. These are model estimates for research, not betting advice, and not a guarantee of any outcome. A selection rated 70% is meant to lose roughly three times in ten.
If gambling is causing you harm: Gambling Help Online (AU) or 1-800-GAMBLER (US).
Licence
MIT for this server. The underlying data is CC BY 4.0 — free to use with attribution to Bet Better.
Available Tools
3 toolsfind_fixtureFind a fixture across leaguesBInspect
Search upcoming fixtures across every league for a team or player name, and return the model's rated selections for the matches that match.
Inputs: query (required), limit.
get_model_picksGet model picks for a leagueAInspect
Return the model's rated selections for a league: estimated win probability, fair decimal odds and a worded confidence (HIGH / LEAN / LONG-SHOT). Contains no bookmaker prices — this is model output only, so it cannot tell you where to bet or at what price.
Inputs: league (required), feed, limit, minProbabilityPct.
list_leaguesList available leaguesAInspect
List every league slug the Bet Better model publishes, for use with the other tools.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: listing leagues, getting picks for a league, and searching fixtures. No overlap in functionality.
All tool names follow a consistent verb_noun pattern (get_model_picks, find_fixture, list_leagues), using underscores and clear verbs.
With only 3 tools, the server is minimal but covers the core querying needs for model predictions. Could benefit from additional tools for direct fixture access or historical data.
Lacks a direct way to retrieve picks for a specific fixture by ID or to get predictions without searching by name. The search tool is a workaround but not a direct lookup.
Maintenance
Related MCP Connectors
Sports odds, player props and source coverage for AI assistants. Connect with your own API key.
Live sports stats and pre-computed analysis for AI assistants across NBA, MLB, NFL, and NHL.
Sports match probabilities and short explanations. Free API key required.
Live sports data: scores, play-by-play, box scores, odds and props. No key needed to start.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP-compatible server that gives AI agents access to alternative sports data across 30+ leagues — odds, events, probabilities, settlement, and futures for prediction markets, DFS platforms, and sportsbooks.2918 PyPIMIT

Odds-API MCP Serverofficial
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.36730 npm3MIT
meridian-edge-mcpofficial
AlicenseAqualityDmaintenanceProvides AI assistants with real-time prediction market consensus data, including probabilities, opportunities, signals, and settlements.517 PyPIMIT- AlicenseBqualityDmaintenanceProvides AI agents with live, grounded sports data including model probabilities, track records, and European soccer and tennis arbitrage opportunities, so they answer from real numbers instead of stale guesses.1368 npm1MIT