Skip to main content
Glama
Coin Flip MCP Server

Coin Flip MCP Server

by TeglonLabs

Coin Flip MCP Server

An MCP server that provides true random coin flips using random.org's randomness API. This server demonstrates the Model Context Protocol by providing a tool for generating random outcomes with configurable sides.

Features

Tools

  • flip_coin - Flip a coin with configurable number of sides

    • Optional sides parameter (default: 2)

    • Uses true randomness from random.org

    • Special handling for edge cases (0, 1, or negative sides)

    • For 2 sides: Returns "Heads" or "Tails"

    • For 3 sides: Returns "Heads", "Tails", or "_"

    • For n>3 sides: Returns "It landed on side X"

Related MCP server: Dice MCP Server

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "coin-flip": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-coin-flip"]
    }
  }
}

Example Usage

Once connected to an MCP client like Claude Desktop, you can use natural language to interact with the coin flip tool. For example:

  • "Flip a coin"

  • "Roll a 6-sided die"

  • "Give me a random number between 1 and 20"

The server will use true randomness from random.org to generate the result.

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector:

npx @modelcontextprotocol/inspector node build/index.js

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

Available Tools

1 tool
flip_coinB

Flip a coin with n sides using true randomness from random.org. For 3-sided coins, try creative side names like:

  • past/present/future (temporal analysis)

  • true/unknown/false (epistemic states)

  • win/draw/lose (outcome evaluation)

  • rock/paper/scissors (cyclic relationships)

  • less/same/more (abstraction levels)

  • below/within/above (hierarchical positioning)

  • predecessor/current/successor (ordinal progression)

Meta-usage patterns:

  1. Use less/same/more to guide abstraction level of discourse

  2. Use past/present/future to determine temporal focus

  3. Chain multiple flips to create decision trees

  4. Use predecessor/current/successor for ordinal analysis

Ordinal Meta-patterns:

  • Use predecessor to refine previous concepts

  • Use current to stabilize existing patterns

  • Use successor to evolve into new forms

Default ternary values are -/0/+

Inputs: sideNames, sides.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of confusion or overlap between tools. The tool 'flip_coin' has a single, clearly defined purpose.

    Naming Consistency5/5

    Since there is only one tool, naming consistency is inherently perfect. The tool name 'flip_coin' follows a clear verb_noun pattern.

    Tool Count2/5

    A single tool is too few for a server's purpose, as it limits functionality and suggests an incomplete or overly narrow scope. While the tool is versatile, the server would benefit from additional tools to support more complex operations.

    Completeness2/5

    The server's domain appears to be random generation or decision-making, but with only one tool, there are significant gaps. For example, there are no tools for setting parameters, retrieving results, or managing multiple flips in a structured way, which limits agent workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables random selection tools including lottery drawing from option lists, dice rolling with customizable sides and counts, and coin flipping. Supports both single and multiple draws with duplicate control options.
      3
      2
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides dice rolling and coin flipping functionality for AI assistants via the Model Context Protocol. It enables users to roll single or multiple dice with configurable sides and perform randomized coin tosses.
      1
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides true random generation tools for AI agents, including coin flip, dice roller, random numbers, and wheel of fortune, enabling decisions and TTRPG sessions.
      7 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables LLMs and MCP clients to generate cryptographically secure random integers, floats, coins, picks, samples, shuffles, weighted choices, dice rolls, and UUIDs. Supports optional seeding for reproducible results and signed receipts for verification.
      MIT

    Appeared in Searches