mcpField
M
mcp-dice: A MCP Server for Rolling Dice

mcp-dice: A MCP Server for Rolling Dice

Local
github.com/yamatonGames & Entertainment4Updated 95w ago
Repository

About mcp-dice: A MCP Server for Rolling Dice

mcp-dice is an MCP server for LLMs that need to roll dice. It parses standard dice notation and reports each roll along with the resulting total.

Key features

  1. 01Standard dice notation parsing
  2. 02Individual roll results
  3. 03Sum, modifier, and total
  4. 04Claude Desktop integration
  5. 05MCP Inspector debugging

Use cases

  1. 01Roll dice for tabletop game checks
  2. 02Inspect individual rolls and totals

MCP support

The MCP server exposes dice rolling to MCP clients. It accepts notation such as `1d20` and returns roll results and totals.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dice": {
      "command": "uvx",
      "args": [
        "mcp-dice"
      ]
    }
  }
}
Run commanduvx mcp-dice

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-dice

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-dice: A MCP Server for Rolling Dice

smithery badge screenshot

A Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to roll dice. It accepts standard dice notation (e.g., 1d20) and returns both individual rolls and their sum.

README image

Features

  • Supports standard dice notation (e.g., 1d20, 3d6, 2d8+1)
  • Returns both individual rolls and the total sum
  • Easy integration with Claude Desktop
  • Compatible with MCP Inspector for debugging

Installation

Installing via Smithery

To install Dice Roller for Claude Desktop automatically via Smithery:

npx @smithery/cli install mcp-dice --client claude

Make uv available: https://docs.astral.sh/uv/getting-started/installation/

Usage

Basic Command Line Usage
# Using uvx
uvx mcp-dice
Input Format

The server accepts a JSON object with a notation field:

{
  "notation": "2d6+3"
}

Example responses:

{
  "rolls": [
    3,
    1
  ],
  "sum": 4,
  "modifier": 3,
  "total": 7,
  "notation": "2d6+3",
  "timestamp": "2024-12-03T16:36:38.926452"
}

Claude Desktop Configuration

Location
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
Examples
macOS Configuration 
{
  "mcpServers": {
    "dice": {
      "command": "uvx",
      "args": ["mcp-dice"]
    }
  }
}
WSL Configuration 
{
  "mcpServers": {
    "dice": {
      "command": "wsl",
      "args": [
        "-e",
        "zsh",
        "-lc",
        "uvx mcp-dice"
      ]
    }
  }
}

Note: Replace zsh with your login shell.

Development and Debugging

Installing Development Dependencies
# Clone the repository
git clone https://github.com/yourusername/mcp-dice
cd mcp-dice

# Install development dependencies
uv pip install -e ".[dev]"
Running Tests
uv run pytest
Using MCP Inspector

The MCP Inspector is a useful tool for debugging your MCP server. Install and run it using npm:

npx @modelcontextprotocol/inspector uvx mcp-dice
Claude Desktop Configuration for Development
macOS configuration (local dev) 
{
  "mcpServers": {
    "dice": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "path/to/mcp-dice-repo",
        "mcp-dice"
      ]
    }
  }
}

Note: Replace path/to/mcp-dice-repo with the path to the repository on your filesystem.

Windows (WSL) configuration (local dev) 
{
  "mcpServers": {
    "dice": {
      "command": "wsl",
      "args": [
        "-e",
        "zsh",
        "-lc",
        "uv run --directory path/to/mcp-dice-repo mcp-dice"
      ]
    }
  }
}

Note: Replace zsh with your login shell. Also, replace path/to/mcp-dice-repo with the path to the repository on your WSL filesystem.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.