Skip to main content
Glama
Betting Method MCP Server

Betting Method MCP Server

by yusakuvol

Betting Method MCP Server

CI npm version Dependabot

An MCP (Model Context Protocol) server that provides calculations for various betting methods. Can be used with Claude Desktop and other MCP-compatible applications.

✨ Now supports 11 betting methods!

🎲 Supported Betting Methods

  • Monte Carlo Method - Sequence-based betting strategy

  • Martingale Method - Double on loss (high risk)

  • Labouchere (Cancellation System) - Flexible sequence strategy

  • Oscar's Grind - Conservative profit-targeting system

  • Cocomo Method - 3x payout Fibonacci progression

  • Goodman (1-2-3-5) - Fixed progression system

  • Fibonacci Method - Fibonacci sequence betting

  • Paroli System - Reverse Martingale (double on wins)

  • D'Alembert Method - Gradual increase/decrease

  • Fixed Percentage Betting - Bankroll percentage strategy (e.g., 10% method)

  • Kelly Criterion - Mathematically optimal bet sizing for long-term growth

Related MCP server: Super Calculadora MCP

📦 Installation

npm install -g betting-method-mcp

Option 2: Use with npx (No installation needed)

npx betting-method-mcp

Option 3: Install from GitHub

git clone https://github.com/yusakuvol/betting-method-mcp.git
cd betting-method-mcp
npm install
npm run build

🚀 Usage

Claude Desktop Configuration

Edit your claude_desktop_config.json:

If installed via npm:

{
  "mcpServers": {
    "betting-method": {
      "command": "betting-method-mcp"
    }
  }
}

If using npx:

{
  "mcpServers": {
    "betting-method": {
      "command": "npx",
      "args": ["betting-method-mcp"]
    }
  }
}

If installed from GitHub:

{
  "mcpServers": {
    "betting-method": {
      "command": "node",
      "args": ["/path/to/betting-method-mcp/build/index.js"]
    }
  }
}

Usage Examples

You can ask Claude Desktop questions like these:

Start a Monte Carlo session with base unit 10
Initialize Martingale with base bet 10, max bet 1000
Start a Fibonacci betting session with base unit 5
Record a win and tell me the next bet amount
Check the current status

🎯 Available Tools

Each betting method provides 4 MCP tools:

  • {method}_init - Initialize a new betting session

  • {method}_record - Record a win/loss and get the next bet amount

  • {method}_status - Check current state (bet amount, profit/loss, etc.)

  • {method}_reset - Reset the session to initial state

Some methods also provide:

  • {method}_statistics - Get detailed session statistics (win rate, ROI, streaks, risk metrics)

Method Names

  • montecarlo - Monte Carlo Method

  • martingale - Martingale Method

  • labouchere - Labouchere (Cancellation System)

  • oscarsgrind - Oscar's Grind

  • cocomo - Cocomo Method

  • goodman - Goodman (1-2-3-5)

  • fibonacci - Fibonacci Method

  • paroli - Paroli System

  • dalembert - D'Alembert Method

  • percentage - Fixed Percentage Betting

  • kelly - Kelly Criterion

📖 Method Details

Monte Carlo Method

Sequence-based betting strategy that manages bet amounts using a number sequence.

How it works:

  1. Set an initial sequence (e.g., [1, 2, 3])

  2. Bet amount = (first number + last number) × base unit

  3. On win: Remove first and last numbers from the sequence

  4. On loss: Add the lost bet amount (in units) to the end of the sequence

  5. Session completes when the sequence has 0 or 1 numbers

Martingale Method

Doubles the bet amount after each loss. High risk strategy.

⚠️ Warning: Bet amounts increase exponentially during losing streaks. Always set limits!

Labouchere (Cancellation System)

Flexible sequence-based strategy where you can set your target profit.

Oscar's Grind

Conservative system that increases bets only after wins, targeting small consistent profits.

Cocomo Method

Fibonacci-style progression designed for 3x payout games.

Goodman (1-2-3-5)

Fixed progression system: 1 → 2 → 3 → 5 units on consecutive wins.

Fibonacci Method

Uses the Fibonacci sequence (1, 1, 2, 3, 5, 8, 13...) to determine bet amounts.

Paroli System (Reverse Martingale)

Doubles bet on wins instead of losses. Less risky than Martingale.

D'Alembert Method

Gradual progression: +1 unit on loss, -1 unit on win.

Fixed Percentage Betting

Bet a fixed percentage of your bankroll (e.g., 10% of current bankroll).

Kelly Criterion

Mathematically optimal betting strategy that calculates the ideal bet size to maximize long-term bankroll growth.

How it works:

  1. Formula: f* = (bp - q) / b

    • f* = optimal bet fraction (percentage of bankroll)

    • b = payout odds (profit multiplier)

    • p = win probability

    • q = loss probability (1 - p)

  2. Fractional Kelly: Use a fraction (0.25, 0.5, etc.) of full Kelly to reduce volatility

  3. Dynamic adjustment: After 30+ games, uses actual win rate instead of estimated probability

  4. Automatically adjusts bet size based on current bankroll and performance

⚠️ Note: Full Kelly (1.0) can be very volatile. Half Kelly (0.5) or Quarter Kelly (0.25) are recommended for practical use.

🤝 Contributing

We welcome contributions! Please see CONTRIBUTING.md for detailed guidelines.

Quick Start for Contributors

  1. Fork the repository

  2. Clone your fork: git clone https://github.com/YOUR_USERNAME/betting-method-mcp.git

  3. Install dependencies: npm install

  4. Create a branch: git checkout -b feature/your-feature-name

  5. Make your changes and add tests

  6. Ensure all checks pass: npm run build && npm test && npm run check

  7. Commit following Conventional Commits

  8. Push and create a Pull Request

Issue Templates

When reporting issues or suggesting features, please use the appropriate template:

  • Bug Report: For reporting bugs or unexpected behavior

  • Feature Request: For suggesting new features or improvements

  • Betting Method: For proposing new betting strategies

See our Issue Templates for more details.

🛠️ Development

Build

npm run build

Development Mode (watch mode)

npm run watch

Local Testing

npm run dev

Testing

This project uses Vitest for testing with 380+ tests across 15 test files.

# Run all tests
npm test

# Run tests in watch mode
npm run test:watch

# Run tests with UI
npm run test:ui

# Run tests with coverage
npm run test:coverage

Code Quality

This project uses Biome for linting and formatting.

# Lint check
npm run lint

# Lint with auto-fix
npm run lint:fix

# Format code
npm run format

# Check formatting
npm run format:check

# Run all checks (lint + format)
npm run check

🤖 AI-Assisted Development

This project includes context files for various AI coding assistants:

Claude Code Custom Command

This project includes a custom /implement command for automatically implementing new betting methods based on GitHub issues.

Usage:

/implement <issue_number>

This will automatically:

  1. Fetch the issue details from GitHub

  2. Generate the method implementation

  3. Add the State interface

  4. Register MCP tools

  5. Create comprehensive tests

  6. Build and run tests

📁 Project Structure

betting-method-mcp/
├── src/
│   ├── index.ts                    # MCP server entry point
│   ├── types.ts                    # Common type definitions
│   ├── helpers/                    # MCP response & tool definition helpers
│   │   ├── __tests__/              # Helper test files
│   │   ├── mcp-response.ts         # Response formatting utilities
│   │   ├── statistics-handler.ts   # Statistics response builder
│   │   └── tool-definitions.ts     # Tool schema factory functions
│   ├── utils/
│   │   └── statistics.ts           # Statistics calculation utilities
│   └── methods/
│       ├── __tests__/              # Method test files (11 files)
│       ├── montecarlo.ts
│       ├── martingale.ts
│       ├── labouchere.ts
│       ├── oscarsgrind.ts
│       ├── cocomo.ts
│       ├── goodman.ts
│       ├── fibonacci.ts
│       ├── paroli.ts
│       ├── dalembert.ts
│       ├── percentage.ts
│       └── kelly.ts
├── .docs/                          # Method specifications (Japanese)
├── build/                          # Compiled files
└── ...

📄 License

MIT

⚠️ Disclaimer

This tool is provided for educational and research purposes only. Use in actual gambling is at your own risk. Betting strategies do not guarantee profits. Please gamble responsibly.

Available Tools

55 tools
cocomo_initB

Initialize a new Cocomo betting session with base unit and optional max bet limit

Inputs: baseUnit (required), maxBet.

cocomo_recordA

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

cocomo_resetA

Reset the current Cocomo session to initial state

Inputs: no named parameters.

cocomo_statisticsA

Get detailed statistics for the current Cocomo session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

cocomo_statusA

Get the current Cocomo session status including current bet, streak, and total profit

Inputs: no named parameters.

dalembert_initB

Initialize a new D'Alembert betting session with base unit and optional max bet limit

Inputs: baseUnit (required), maxBet.

dalembert_recordA

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

dalembert_resetA

Reset the current D'Alembert session to initial state

Inputs: no named parameters.

dalembert_statisticsA

Get detailed statistics for the current D'Alembert session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

dalembert_statusA

Get the current D'Alembert session status including current bet and total profit

Inputs: no named parameters.

fibonacci_initB

Initialize a new Fibonacci betting session with base unit and optional maximum index

Inputs: baseUnit (required), maxIndex.

fibonacci_recordC

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

fibonacci_resetB

Reset the current Fibonacci session to initial state

Inputs: no named parameters.

fibonacci_statisticsA

Get detailed statistics for the current Fibonacci session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

fibonacci_statusA

Get the current Fibonacci session status including sequence position, current bet, and total profit

Inputs: no named parameters.

goodman_initB

Initialize a new Goodman (1-2-3-5) betting session with a base unit amount

Inputs: baseUnit (required).

goodman_recordB

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

goodman_resetA

Reset the current Goodman session to initial state

Inputs: no named parameters.

goodman_statisticsA

Get detailed statistics for the current Goodman session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

goodman_statusA

Get the current Goodman session status including current bet, step, win streak, and total profit

Inputs: no named parameters.

kelly_initA

Initialize a new Kelly Criterion betting session with bankroll, win probability, payout odds, and optional fractional Kelly

Inputs: payoutOdds (required), winProbability (required), initialBankroll (required), maxBet, +2 more.

kelly_recordA

Record a bet result (win or loss) and get the next recommended bet amount

Inputs: result (required), actualPayout.

kelly_resetA

Reset the current Kelly Criterion session to initial state

Inputs: no named parameters.

kelly_statisticsA

Get detailed statistics for the current Kelly Criterion session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

kelly_statusA

Get the current Kelly Criterion session status including bankroll, recommended bet, and statistics

Inputs: no named parameters.

labouchere_initB

Initialize a new Labouchere betting session with target profit and optional sequence

Inputs: baseUnit (required), targetProfit (required), initialSequence, maxSequenceLength.

labouchere_recordA

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

labouchere_resetA

Reset the current Labouchere session to initial state

Inputs: no named parameters.

labouchere_statisticsB

Get detailed statistics for the current Labouchere session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

labouchere_statusA

Get the current Labouchere session status including sequence, current bet, and total profit

Inputs: no named parameters.

martingale_initB

Initialize a new Martingale betting session with base unit and optional limits

Inputs: baseUnit (required), maxBet, maxLossStreak.

martingale_recordA

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

martingale_resetB

Reset the current Martingale session to initial state

Inputs: no named parameters.

martingale_statisticsA

Get detailed statistics for the current Martingale session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

martingale_statusA

Get the current Martingale session status including current bet, streak, and total profit

Inputs: no named parameters.

montecarlo_initB

Initialize a new Monte Carlo betting session with a base unit amount

Inputs: baseUnit (required).

montecarlo_recordB

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

montecarlo_resetA

Reset the current Monte Carlo session to initial state

Inputs: no named parameters.

montecarlo_statisticsA

Get detailed statistics for the current Monte Carlo session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

montecarlo_statusA

Get the current Monte Carlo session status including sequence, current bet, and total profit

Inputs: no named parameters.

oscarsgrind_initB

Initialize a new Oscar's Grind betting session with base unit and optional parameters

Inputs: baseUnit (required), maxBetUnits, targetProfitUnits.

oscarsgrind_recordB

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

oscarsgrind_resetA

Reset the current Oscar's Grind session to initial state

Inputs: no named parameters.

oscarsgrind_statisticsA

Get detailed statistics for the current Oscar's Grind session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

oscarsgrind_statusA

Get the current Oscar's Grind session status including current bet, profit, and sessions completed

Inputs: no named parameters.

paroli_initC

Initialize a new Paroli betting session with base unit and optional target win streak

Inputs: baseUnit (required), targetWinStreak.

paroli_recordB

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

paroli_resetB

Reset the current Paroli session to initial state

Inputs: no named parameters.

paroli_statisticsA

Get detailed statistics for the current Paroli session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

paroli_statusA

Get the current Paroli session status including current bet, win streak, and total profit

Inputs: no named parameters.

percentage_initB

Initialize a new Percentage (Fixed Percentage Betting) session with bankroll, percentage, and minimum bet

Inputs: minBet (required), betPercentage (required), initialBankroll (required).

percentage_recordB

Record a bet result (win or loss) and get the next bet amount

Inputs: result (required).

percentage_resetA

Reset the current Percentage betting session to initial state

Inputs: no named parameters.

percentage_statisticsA

Get detailed statistics for the current Percentage betting session including win rate, ROI, streaks, and risk metrics

Inputs: no named parameters.

percentage_statusA

Get the current Percentage betting session status including bankroll, current bet, and profit percentage

Inputs: no named parameters.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 55 tools

    Disambiguation5/5

    Each tool is uniquely identified by the betting method prefix (e.g., cocomo, dalembert) and an action suffix (init, record, etc.), making it impossible to confuse tools from different methods or actions.

    Naming Consistency5/5

    All tools follow a strict snake_case pattern of {method}_{action}, with identical action sets for each method, ensuring high predictability and consistency.

    Tool Count4/5

    With 55 tools covering 11 distinct betting methods, each requiring 5 lifecycle actions, the number is appropriate for the comprehensive scope, though slightly high for a single server.

    Completeness5/5

    For each betting method, the tools provide full session management: initialization, result recording, reset, statistics, and status monitoring, covering all essential operations without obvious gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      A simple demonstration MCP server that provides basic utility tools including dice rolling and number addition functionality. This server serves as a tutorial example for setting up both local and remote MCP servers using FastMCP.
      3
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server providing over 30 mathematical and statistical tools, enabling language models to perform calculations, trigonometry, statistics, combinatorics, and list operations through natural language.
      ISC
    • A
      license
      A
      quality
      C
      maintenance
      MCP server that connects AI assistants to the Statos football analytics platform, enabling natural language queries for match predictions, betting picks, league information, and admin market-suppression controls.
      7
      6 npm
      MIT

    Appeared in Searches