MCP server
by lpbayliss
Try our online dice roller for cryptographically secure virtual dice, supporting standard and Fate dice for all your tab
Provides cryptographically secure dice rolling with standard notation support for tabletop RPGs and games. Parses notation like '2d6+4' and generates random rolls with accurate probability distributions.
Dice Roller is a community-built MCP server published by lpbayliss that provides AI assistants with tools and capabilities via the Model Context Protocol. Try our online dice roller for cryptographically secure virtual dice, supporting standard and Fate dice for all your tab It is categorized under other. This server exposes 2 tools that AI clients can invoke during conversations and coding sessions.
You can install Dice Roller in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Dice Roller is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Dice Roller reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We evaluated Dice Roller against two servers with overlapping tools; this profile had the clearer scope statement.
I recommend Dice Roller for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
We evaluated Dice Roller against two servers with overlapping tools; this profile had the clearer scope statement.
Useful MCP listing: Dice Roller is the kind of server we cite when onboarding engineers to host + tool permissions.
Dice Roller is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Useful MCP listing: Dice Roller is the kind of server we cite when onboarding engineers to host + tool permissions.
According to our notes, Dice Roller benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Dice Roller has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Dice Roller reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
showing 1-10 of 46
A Model Context Protocol (MCP) server for simulating dice rolls with support for standard dice notation and Fate/Fudge dice.
2d6, 1d20+5, or 4dFThis MCP server provides two main tools:
Parses a dice notation string and returns the structured representation.
parse_dice_roll_notation
input: { notation: "3d6+4" }
output: { type: "standard", count: 3, sides: 6, modifier: 4 }
Rolls dice based on a dice roll configuration and returns the results.
dice_roll
input: { type: "standard", count: 3, sides: 6, modifier: 4 }
output: { rolls: [5, 2, 6], total: 17, original: "3d6+4" }
Add this server to your Claude Desktop configuration:
{
"mcpServers": {
"dice": {
"command": "npx",
"args": ["-y", "server-dice-roll"]
}
}
}
# Install globally
npm install -g server-dice-roll
# Run the server
mcp-server-dice-roll
# Or run directly with npx
npx server-dice-roll
Dice notation is a system used in tabletop role-playing games to represent different dice rolls.
The standard format is NdS+M where:
N is the number of dice to roll (optional, defaults to 1)d indicates a die rollS is the number of sides on each die+M is a modifier to add to the total (optional)Examples:
d6 - Roll one 6-sided die2d10 - Roll two 10-sided dice and sum the results3d8+5 - Roll three 8-sided dice, sum the results, and add 5Fate dice (also known as Fudge dice) are special 6-sided dice with values of -1, 0, and +1 (two sides each).
Format: NdF where:
N is the number of dice to rolldF indicates Fate diceExample:
4dF - Roll four Fate dice (results in values between -4 and +4)This project is licensed under the MIT License - see the LICENSE.md file for details.
Created by Luke Bayliss hello@lukebayliss.com
This project uses a single integrated workflow for versioning, releases, and publishing:
Version Bump Labels: Each PR to the main branch should include exactly one version bump label:
patch - For backwards-compatible bug fixesminor - For backwards-compatible new featuresmajor - For breaking changespatch is applied by defaultSequential Workflow: The integrated Release and Publish workflow consists of three sequential jobs:
Automated Triggers: The workflow runs automatically in these scenarios:
All these steps run in a coordinated workflow with proper dependencies to ensure reliability.
All PRs should include exactly one version bump label (patch, minor, or major). If no label is specified, the system will automatically add the patch label as the default. PRs with multiple version labels will still be blocked from merging.
To manually trigger a version bump without creating a PR:
The rest of the process (creating release and publishing) will happen automatically.
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.