A single job, done outside the model.

The pitch is narrow and honest: language models draw numbers unevenly, and this replaces that draw with one from random.org's atmospheric noise. There is no configuration and no key, but there is a build step and a network dependency, so it belongs in setups where the fairness of the draw actually matters.

What it is

An MCP server that fetches true random numbers from random.org, which derives them from atmospheric noise. The repository opens with a distribution chart of 100 numbers in the range 1-100 drawn from three popular LLMs, to show the bias it exists to remove.

What you get

Random numbers from an external physical source rather than from the model's own token distribution
A stdio server that plugs into any MCP client through a plain command entry

Requirements

No account and no key. Clone the repository, run npm install and npm run build, then point your client at the absolute path of build/index.js with node. The package is mcp-random-number (1.0.0 in package.json).

Setup effort

Build from source — git clone https://github.com/maxbogo/mcp-random-number.git

See installation options

USE CASES

01

Picking a winner without arguing about fairness

Draw the number from an external physical source so the result does not depend on how the model happens to weight digits.

02

Sampling from a list during analysis

Ask for indices in a range and use them to select rows, instead of letting the model choose which items look representative.

03

Seeding a simulation or a game turn

Take the starting value from random.org so repeated runs in one conversation do not drift toward the model's favourite numbers.

INSTALLATION

Connect your client

You clone and build this one yourself.

Server setup

TERMINAL

   git clone https://github.com/maxbogo/mcp-random-number.git
   cd mcp-random-number
   npm install
   npm run build

MCP Clients

Any MCP client

ANY MCP CLIENT · JSON

{
  "mcpServers": {
    "mcp-random-number": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_MCP_RANDOM_NUMBER>/build/index.js"
      ]
    }
  }
}

MCP Random Number