sports-betting-mcp

The first MCP server for sports betting. Give any AI agent live access to picks, odds, injuries, line movement, and game analysis across NBA, NHL, NCAAB, and MLB.

mcp-name: io.github.seang1121/sports-betting-mcp

Track Record

Every pick is logged before tip-off and resolved against final scores. Nothing is cherry-picked.

Results by Sport

All results are queryable in real-time through the get_win_rate tool. Ask your AI agent to pull the latest numbers -- they update after every game.

Why This Exists

Sportsbooks have the data. Bettors have opinions. AI agents have reasoning -- but no access to either.

This server is the bridge.

Before sports-betting-mcp, an AI agent could talk about sports betting but couldn't actually look at today's odds, check injury reports, analyze line movement, or generate a pick with a documented edge. It was guessing. Now it has a direct feed.

The system behind this MCP server runs a 12-agent analysis pipeline on every game: each agent evaluates a different angle (momentum, matchups, injuries, public betting %, sharp money, rest advantage, and more), then a consensus engine synthesizes them into a single pick with a confidence score and edge breakdown.

Works With

Any client that supports the Model Context Protocol can connect:

One install. Works everywhere.

Quick Start

Install

pip install sports-betting-mcp

Configure

export SPORTS_BETTING_API_URL=https://sportsbettingaianalyzer.com
export SPORTS_BETTING_API_KEY=your_api_key
sports-betting-mcp

Add to Your MCP Client

Drop this into your MCP config (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "sports-betting": {
      "command": "sports-betting-mcp",
      "env": {
        "SPORTS_BETTING_API_URL": "https://sportsbettingaianalyzer.com",
        "SPORTS_BETTING_API_KEY": "your_api_key"
      }
    }
  }
}

Get a free API key at sportsbettingaianalyzer.com/account/api-keys.

Available Tools

12 tools. Every call returns structured data that AI agents can reason over, display, or act on.

Visual Bet Slips

The get_top_pick and get_todays_picks tools return rendered bet slip images directly in chat. No links, no redirects -- the card shows up inline with the pick details, confidence score, and recommended bet.

How the Analysis Works

Each game runs through a multi-agent pipeline:

1. 12 specialized agents evaluate the game independently -- covering momentum, matchups, injuries, rest, travel, public betting percentages, sharp money indicators, historical trends, and more.

2. A consensus engine synthesizes all 12 opinions into a single pick with a confidence score.

3. Edge calculation compares the model's implied probability against the current market line.

4. Picks are logged before tip-off and resolved against final scores. No retroactive edits.

The confidence score and edge breakdown are included in every pick response, so your AI agent can filter, rank, or explain the reasoning behind any recommendation.

Tech Stack

Who Built This

Built by a developer who got tired of manually checking odds across apps and spreadsheets. The data exists, the analysis can be automated, and AI agents are the right interface -- but nobody had connected the pipes.

This started as a personal tool to automate a nightly betting research workflow. When MCP launched and made it possible to expose that system to any AI agent, the decision to publish was obvious.

Requirements

• Python 3.10+

• A free API key from sportsbettingaianalyzer.com

License

MIT