Mcp Randoom — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Randoom (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Model Context Protocol (MCP) server that provides true random generation tools for your AI agents. Whether you need an AI to make a decision for you, or you want it to act as a Dungeon Master for your next D&D session, mcp-randoom has you covered.
1d20, 2d6, 4d8). Great for TTRPG sessions where the AI plays the DM or a player.You can run this MCP server directly using bunx without needing to install it globally.
bunx github:ringotypowriter/mcp-randoomTo use this with Claude Desktop, add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"randoom": {
"command": "bunx",
"args": [
"github:ringotypowriter/mcp-randoom"
]
}
}
}coin_flipFlips a coin and returns "Heads" or "Tails".
dice_rollRolls dice based on input notation.
dice (string) - e.g., "1d20", "2d6".random_numberGenerates a random number.
min (number)max (number)integer (boolean, default: true)wheel_spinSpins a wheel to randomly select one option from a list.
options (array of strings) - List of options (must be > 3).MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.