Skip to main content
Glama
OO-EPC-MCP

OO-EPC-MCP

by i0ivi0i

OO-EPC-MCP πŸ“βš‘

License: MIT MCP Python FastMCP

A lightweight, high-performance Model Context Protocol (MCP) server for sports betting analytics and actuarial mathematics.

Built on FastMCP / official MCP Python SDK (MCPServer). Exposes pure mathematical algorithms with zero external API calls, zero secret keys, and sub-millisecond local deterministic execution.


πŸ› οΈ Tools Provided

1. devig_oo_epc

Calculates true unbiased 1X2 probabilities from 3-way bookmaker odds using the Tokyo University Shota Goto (2026) OO-EPC (Odds-on Equal Profit Margin) convex optimization algorithm.

  • Parameters:

    • home_odds (float): Decimal odds for Home Win (e.g. 1.51)

    • draw_odds (float): Decimal odds for Draw (e.g. 4.30)

    • away_odds (float): Decimal odds for Away Win (e.g. 4.60)

  • Returns:

    • Unbiased true probability vector (probabilities, percentages)

    • Bookmaker overround / margin (margin, margin_pct)

    • Formatted display text (63.4% / 19.1% / 17.5%)

    • Structured parameter validation error payload if any odd is <= 1.0

2. devig_oo_epc_batch (New in v1.1.0)

Single-call batch OO-EPC de-vigging across up to 21 bookmakers' opening and latest 1X2 odds, with automatic opening-to-latest probability shift (delta_prob_pct) and Pinnacle (cid=177) benchmark scissor-gap (gap_vs_pin_latest_pct) calculation.

  • Parameters:

    • items (List[Dict[str, Any]]): List of bookmaker items, each accepting cid, name, open ([home_odds, draw_odds, away_odds]), and latest ([home_odds, draw_odds, away_odds]).

  • Returns:

    • pinnacle_anchor: De-vigged latest benchmark probabilities when Pinnacle (cid=177 / "平博") is present in the batch

    • results: Per-bookmaker opening/latest OO-EPC probabilities, margins, delta_prob_pct, delta_margin_pct, and gap_vs_pin_latest_pct

    • errors: Self-correcting field-level validation diagnostics for any malformed entry

3. poisson_dixon_coles

Calculates bivariate Poisson match score probabilities with Dixon-Coles low-score factor adjustments (handling the systematic underestimation of low-scoring draws like 0-0, 1-1).

  • Parameters:

    • home_lambda (float): Expected goals for Home Team (e.g. 1.85)

    • away_lambda (float): Expected goals for Away Team (e.g. 0.95)

    • max_goals (int, optional, default 8): Upper bound of goals evaluated per side

    • top_n (int, optional, default 6): Top $N$ most probable scorelines

  • Returns:

    • Expected total goals

    • True 1X2 win/draw/loss probability distribution

    • Top scorelines ranked by probability with exact percentages and fair odds


Related MCP server: PredictionMarketsPicks Quant

πŸš€ Quick Start & Installation

Option 1: Run with uv (Recommended)

No manual environment setup needed:

uv run server.py

Option 2: Run with standard pip

pip install -r requirements.txt
python server.py

πŸ”Œ Client Integration

Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "sports-math": {
      "command": "python",
      "args": [
        "/path/to/OO-EPC-MCP/server.py"
      ]
    }
  }
}

Hermes Agent

Add this to your ~/.hermes/config.yaml:

mcp_servers:
  sports-math:
    command: python
    args:
      - /path/to/OO-EPC-MCP/server.py

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "sports-math": {
      "command": "python",
      "args": ["/path/to/OO-EPC-MCP/server.py"]
    }
  }
}

πŸ“š Mathematical Citations

  • Goto, Shota (2026). Odds-on Equal Profit Margin (OO-EPC) Method for Multi-way Betting Market De-vigging. The University of Tokyo.

  • Dixon, M. J., & Coles, S. G. (1997). Modelling Association Football Scores and Inefficiencies in the Football Betting Market. Applied Statistics (Journal of the Royal Statistical Society: Series C), 46(2), 265–280.


πŸ“„ License

MIT License Β© 2026 i0ivi0i

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Quant tools for AI agents on Kalshi & Polymarket. 34 tools, 27 free with no key: EV, Kelly sizing, Bayes updates, odds conversion, base-rate gaps, combo grading, Fed odds, NFL and NHL models, 2026 Senate race odds, Kalshi weather board and Kalshi 15-minute markets + perps (live board + liquidation estimates). Pro adds commodity + NFL edge models, mispricing scanner and alerts.
      44
      38 npm
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      Enables fetching sports odds from The Odds API and removing bookmaker margin (vig) to compute fair probabilities, with tools for today's MLB games, processed odds, and consensus lines.
      6
      -
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables users to estimate football match probabilities using a Dixon-Coles model, compare them to de-vigged bookmaker odds, and identify value bets from Claude Desktop.
      -