sports-betting-mcp

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

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

---

What It Does

Connects any MCP-compatible AI agent to a live sports betting analysis system. Every pick is logged before tip-off and resolved against final scores. Nothing is cherry-picked.

Metric	Value
Sports Covered	NBA, NHL, NCAAB, MLB
Bet Types	Moneyline, Spread, Totals
Pick Source	12-agent consensus model
Total Picks	3,859+ resolved
Platform Users	30
Tools	12 MCP tools
Auth	API key (X-API-Key header)

Results by Sport

Sport	Picks	Wins	Win Rate
NBA	1,267	762	60.1%
NHL	1,148	656	57.1%
NCAAB	1,149	549	47.8%
MLB	283	109	38.5% (launched Apr 2026)

All results are queryable in real-time via the get_win_rate tool. Numbers update after every game.

---

Quick Start

Install

pip install sports-betting-mcp

Add to Your MCP Client

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

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

Environment Variables

Variable	Required	Description
SPORTS_BETTING_API_KEY	Yes	Your API key for authentication
SPORTS_BETTING_API_URL	No	API base URL (defaults to http://localhost:5000)

---

Works With

Any client that supports the Model Context Protocol:

Client	Status
Claude Desktop	Fully supported
Cursor	Fully supported
Windsurf	Fully supported
Claude Code (CLI)	Fully supported
Any MCP Client	Fully supported via stdio transport

---

Available Tools

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

Picks & Analysis

Tool	What It Does
get_todays_picks	All AI picks with confidence scores and edge breakdowns, filterable by sport
get_top_pick	Single highest-confidence pick of the day
get_pending_picks	Currently unresolved picks that are still in play
get_completed_picks	Recently resolved picks with W/L results -- verify the track record
analyze_game	Full 12-agent analysis on any game: consensus pick + edge breakdown

Odds & Market Data

Tool	What It Does
get_live_odds	Live moneyline, spread, and totals for today's games
get_alerts	Active alerts from the multi-agent system (line moves, injury impacts)

Performance & Stats

Tool	What It Does
get_win_rate	Win rate with breakdown by sport and bet type
get_model_stats	Model performance: total picks, last-20 win rate, confidence tier breakdown
get_leaderboard	User rankings by win rate
get_system_status	Health check -- uptime, database, scheduler status

---

How the Analysis Works

Each game runs through a multi-agent pipeline:

1. 12 specialized agents evaluate the game independently -- covering momentum, matchups, inj

... View full README on GitHub