dice-rolling-mcp

dice-rolling-mcp

3.2

If you are the rightful owner of dice-rolling-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A TypeScript-based Model Context Protocol (MCP) server that provides comprehensive dice rolling capabilities to AI assistants, supporting standard dice notation with advanced mechanics commonly used in tabletop gaming.

Dice Rolling MCP Server

A comprehensive TypeScript-based Model Context Protocol (MCP) server that provides advanced dice rolling capabilities for AI assistants. Perfect for tabletop gaming, RPGs, and any application requiring sophisticated random number generation with gaming mechanics.

The Problem: LLMs Can't Actually Roll Dice

When you ask an AI assistant to "roll dice," they don't actually roll anything. Large Language Models are deterministic systems that generate responses based on patterns in their training data. When asked to roll a d20, they might respond with something like "I rolled a 14" - but that number was generated through text prediction, not random number generation.

This creates several problems:

  • No True Randomness: Results aren't genuinely random and may follow predictable patterns
  • Gaming Integrity: Critical for tabletop RPGs where fair dice rolls affect gameplay
  • Simulation Accuracy: Statistical simulations require proper random number generation
  • Reproducibility Issues: Same prompts might yield suspiciously similar "random" results

The Solution: Real Dice for AI

This MCP server acts as a bridge between AI assistants and actual random number generation. Think of it as giving your AI assistant a real set of dice instead of asking them to imagine rolling.

How it works:

  • AI assistant receives dice notation (e.g., "3d6+2")
  • MCP server parses the request and generates cryptographically secure random numbers
  • Real dice mechanics are applied (advantage, exploding dice, rerolls, etc.)
  • Genuine random results are returned to the AI

The result: AI assistants can now provide truly random dice rolls with mathematical integrity, making them suitable for actual gaming, simulations, and any application requiring authentic randomness.

Features

Standard Dice Notation

  • Basic rolls: 1d20, 3d6, 2d10
  • Modifiers: 1d20+5, 2d6-3, 1d8*2
  • Multiple dice types: 1d20+2d6+3
  • Percentile dice: 1d% (d100)
  • Fudge dice: 4dF (Fate/Fudge system)

Advanced Mechanics

  • Advantage/Disadvantage: 2d20kh1 (keep highest), 2d20kl1 (keep lowest)
  • Drop mechanics: 4d6dl1 (drop lowest), 4d6dh1 (drop highest)
  • Exploding dice: 3d6! (reroll and add on maximum)
  • Reroll mechanics: 4d6r1 (reroll 1s)
  • Success counting: 5d10>7 (count successes ā‰„7)

MCP Tools

dice_roll

Executes dice rolls using standard notation with optional labeling and verbose output.

Parameters:

  • notation (required): Dice notation string (e.g., "3d6+2")
  • label (optional): Descriptive label for the roll
  • verbose (optional): Show detailed breakdown of individual dice
dice_validate

Validates dice notation without executing the roll, providing detailed breakdown of what the notation means.

Parameters:

  • notation (required): Dice notation string to validate

Installation

git clone <repository-url>
cd dice-rolling-mcp
npm install
npm run build

Usage

With Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "dice-roller": {
      "command": "node",
      "args": ["path/to/dice-rolling-mcp/dist/index.js"]
    }
  }
}

Platform-specific examples:

Windows (WSL):

{
  "mcpServers": {
    "dice-roller": {
      "command": "wsl",
      "args": ["node", "/path/to/dice-rolling-mcp/dist/index.js"]
    }
  }
}

macOS/Linux:

{
  "mcpServers": {
    "dice-roller": {
      "command": "node",
      "args": ["/path/to/dice-rolling-mcp/dist/index.js"]
    }
  }
}

Standalone Server

npm run start

Examples

Basic Rolling

Human: Roll 3d6+2 for damage
Assistant: You rolled 3d6+2 for damage:
šŸŽ² Total: 13
šŸ“Š Breakdown: 3d6:[4,2,5] + 2

Advantage System

Human: Roll 2d20kh1+5 for attack with advantage
Assistant: You rolled 2d20kh1+5 for attack with advantage:
šŸŽ² Total: 23
šŸ“Š Breakdown: 2d20:[12,18] keep highest + 5

Validation

Human: Is "4d6kh3+2d8+5" valid dice notation?
Assistant: āœ… Valid dice notation: 4d6kh3+2d8+5

Breakdown:
ā€¢ 4d6 (keep highest 3)
ā€¢ 2d8
ā€¢ Modifier: +5

Architecture

Core Components

  • Parser (src/parser/): Tokenizes and parses dice notation using regex-based parsing
  • Roller (src/roller/): Executes dice expressions with cryptographically secure random number generation
  • MCP Server (src/index.ts): Implements the Model Context Protocol for AI assistant integration
  • Type System (src/types.ts): Comprehensive TypeScript definitions for all dice mechanics

Key Design Decisions

  • Security: Uses Node.js crypto.randomInt() for cryptographically secure randomness
  • Extensibility: Modular architecture supports easy addition of new dice mechanics
  • Compatibility: ES2022 target with fallbacks for broader Node.js version support
  • Type Safety: Full TypeScript implementation with strict type checking

Testing

npm test

The test suite covers:

  • Dice notation parsing for all supported mechanics
  • Roll execution with mocked random number generation
  • Edge cases and error handling
  • MCP protocol compliance

Development

Project Structure

dice-rolling-mcp/
ā”œā”€ā”€ src/
ā”‚   ā”œā”€ā”€ index.ts              # MCP server implementation
ā”‚   ā”œā”€ā”€ parser/               # Dice notation parser
ā”‚   ā”œā”€ā”€ roller/               # Dice rolling engine
ā”‚   ā”œā”€ā”€ statistics/           # Statistical analysis tools
ā”‚   ā””ā”€ā”€ types.ts              # TypeScript definitions
ā”œā”€ā”€ __tests__/                # Test suite
ā”œā”€ā”€ dist/                     # Compiled JavaScript
ā””ā”€ā”€ examples/                 # Usage examples

Adding New Mechanics

  1. Extend the DiceTerm interface in types.ts
  2. Update the parser regex in dice-notation-parser.ts
  3. Implement the mechanic in dice-roller.ts
  4. Add comprehensive tests

Configuration

The server supports various configuration options through the DiceRollerConfig interface:

  • Maximum dice count per roll
  • Maximum die size
  • Random number source selection
  • History size limits

Technical Specifications

  • Language: TypeScript 5.8+
  • Runtime: Node.js 18+ (tested with v24.0.2)
  • Protocol: MCP (Model Context Protocol) 2024-11-05
  • Dependencies: Minimal (zod, @modelcontextprotocol/sdk)
  • Module System: ES Modules
  • Test Framework: Jest with ts-jest

Security Considerations

  • Input validation prevents malicious dice expressions
  • Resource limits prevent DoS through extremely large rolls
  • Cryptographically secure random number generation
  • No external network dependencies

Author

Jim McQuillan

License

ISC

Contributing

Contributions welcome! Please ensure:

  • All tests pass (npm test)
  • Code follows existing patterns and conventions
  • New features include appropriate test coverage
  • TypeScript strict mode compliance