Sports Predictions API
& MCP Server
Full probability distributions for every outcome.
REST API for your stack. MCP Server for AI agents.
Tennis · Football · NBA
Two Ways to Access the Data
Same probabilistic models, two integration paths depending on your use case.
REST API
Standard JSON endpoints. Query predictions by sport, date, and match. Integrate into dashboards, analytics pipelines, or any application that speaks HTTP.
MCP Server
A Model Context Protocol server that exposes prediction tools directly to AI agents. Connect it to Claude, OpenClaw, or any MCP-compatible client.
What MCP Integration Looks Like
When an AI agent has access to PredixSport's MCP server, it can retrieve live probabilistic predictions as part of a natural conversation. No manual API calls, no copy-pasting data.
get_tennis_prediction33 games: 5% · 35: 10% · 37: 15% · 38: 14% · 39: 12% · 40: 9% · 41+: 10%
The probability of going over 36.5 is 63%. This is a best-of-5 on clay, so longer matches are plausible given both players' baseline-heavy game.
This works with any MCP-compatible client: Claude Desktop, OpenClaw, custom agents built with the Agent SDK, or your own CLI tools. The MCP server exposes tools like get_tennis_prediction, get_nba_prediction, and get_football_prediction — the agent decides when and how to call them.
Available Models
Each prediction includes an expected value and a full probability distribution across discrete outcome buckets.
{ "match": "Boston Celtics vs Golden State Warriors", "date": "2025-04-06", "winner": { "boston_celtics": 0.61, "golden_state_warriors": 0.39 }, "total_points": { "expected": 224.5, "distribution": { "210": 0.04, "215": 0.07, "220": 0.12, "225": 0.18, "230": 0.17, "235": 0.14, "240+": 0.28 }, "over_222_5": 0.64 }, "spread": { "expected": 5.2, "distribution": { "-6": 0.05, "-3": 0.09, "0": 0.14, "+3": 0.18, "+6": 0.22, "+9": 0.17, "+12+": 0.15 } } }
{ "match": "Inter vs AC Milan", "league": "Serie A", "date": "2025-04-06", "result": { "home_win": 0.46, "draw": 0.27, "away_win": 0.27 }, "corners": { "expected": 10.7, "distribution": { "7": 0.05, "8": 0.08, "9": 0.12, "10": 0.17, "11": 0.18, "12": 0.15, "13+": 0.25 }, "over_9_5": 0.75 }, "total_shots": { "expected": 27.3, "distribution": { "22": 0.06, "24": 0.11, "26": 0.16, "27": 0.14, "28+": 0.31 }, "over_24_5": 0.75 } }
{ "match": "Djokovic vs Alcaraz", "tournament": "Roland Garros 2025", "surface": "clay", "winner": { "djokovic": 0.48, "alcaraz": 0.52 }, "total_games": { "expected": 38.4, "distribution": { "33": 0.05, "35": 0.10, "37": 0.15, "38": 0.14, "39": 0.12, "40": 0.09, "41+": 0.10 }, "over_36_5": 0.63 }, "aces_djokovic": { "expected": 11.2, "over_10_5": 0.72 }, "double_faults_alcaraz": { "expected": 3.1, "over_2_5": 0.67 } }
Coverage
Models are trained on 30,000+ ATP and 40,000+ NBA historical matches. Predictions refresh after each matchday using ELO and Glicko-2 rating systems.
Get on the List
We are shaping the API based on early feedback. Tell us what you would use it for and we will reach out when access opens.
Need something specific?
Custom endpoints, additional leagues, or volume pricing — reach out directly.