betting-method-mcp
v0.1.0
Published
MCP server for calculating various betting methods (Monte Carlo, Martingale, etc.)
Maintainers
Readme
Betting Method MCP Server
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 10 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)
📦 Installation
Option 1: Install from npm (Recommended)
npm install -g betting-method-mcpOption 2: Use with npx (No installation needed)
npx betting-method-mcpOption 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 10Initialize Martingale with base bet 10, max bet 1000Start a Fibonacci betting session with base unit 5Record a win and tell me the next bet amountCheck 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
Method Names
montecarlo- Monte Carlo Methodmartingale- Martingale Methodlabouchere- Labouchere (Cancellation System)oscarsgrind- Oscar's Grindcocomo- Cocomo Methodgoodman- Goodman (1-2-3-5)fibonacci- Fibonacci Methodparoli- Paroli Systemdalembert- D'Alembert Methodpercentage- Fixed Percentage Betting
📖 Method Details
Monte Carlo Method
Sequence-based betting strategy that manages bet amounts using a number sequence.
How it works:
- Set an initial sequence (e.g.,
[1, 2, 3]) - Bet amount = (first number + last number) × base unit
- On win: Remove first and last numbers from the sequence
- On loss: Add the lost bet amount (in units) to the end of the sequence
- 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).
🛠️ Development
Build
npm run buildDevelopment Mode (watch mode)
npm run watchLocal Testing
npm run devTesting
This project uses Vitest for testing with 234+ tests across 10 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:coverageCode 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.md - Comprehensive context for Claude AI assistants
- AGENT.md - General context for any AI agent
- .github/copilot-instructions.md - GitHub Copilot instructions
- .cursorrules - Cursor AI rules
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:
- Fetch the issue details from GitHub
- Generate the method implementation
- Add the State interface
- Register MCP tools
- Create comprehensive tests
- Build and run tests
📁 Project Structure
betting-method-mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── types.ts # Common type definitions
│ └── methods/
│ ├── __tests__/ # Vitest test files (10 files)
│ ├── montecarlo.ts
│ ├── martingale.ts
│ ├── labouchere.ts
│ ├── oscarsgrind.ts
│ ├── cocomo.ts
│ ├── goodman.ts
│ ├── fibonacci.ts
│ ├── paroli.ts
│ ├── dalembert.ts
│ └── percentage.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.
