Coin Flip MCP Server
抛硬币 MCP 服务器
一个使用 random.org 随机性 API 提供真随机抛硬币功能的 MCP 服务器。该服务器通过提供可配置方向的随机结果生成工具来演示模型上下文协议 (MCP)。
特征
工具
flip_coin- 抛一枚可配置面数的硬币可选
sides参数(默认值:2)使用来自 random.org 的真正随机性
对边缘情况(0、1 或负数)的特殊处理
对于 2 面:返回“正面”或“反面”
对于三面:返回“正面”、“反面”或“_”
对于 n>3 面:返回“它落在 X 面上”
Related MCP server: Dice MCP Server
发展
安装依赖项:
npm install构建服务器:
npm run build对于使用自动重建的开发:
npm run watch安装
要与 Claude Desktop 一起使用,请添加服务器配置:
在 MacOS 上: ~/Library/Application Support/Claude/claude_desktop_config.json
在 Windows 上: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"coin-flip": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-coin-flip"]
}
}
}示例用法
连接到 Claude Desktop 等 MCP 客户端后,您可以使用自然语言与抛硬币工具进行交互。例如:
“抛硬币”
“掷一个六面骰子”
“给我一个 1 到 20 之间的随机数”
服务器将使用来自 random.org 的真正随机性来生成结果。
调试
由于 MCP 服务器通过 stdio 进行通信,调试起来可能比较困难。我们建议使用MCP Inspector :
npx @modelcontextprotocol/inspector node build/index.js贡献
欢迎贡献代码!欢迎提交 Pull 请求。
执照
麻省理工学院
Available Tools
1 toolflip_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:
Use less/same/more to guide abstraction level of discourse
Use past/present/future to determine temporal focus
Chain multiple flips to create decision trees
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
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool 'flip_coin' has a single, clearly defined purpose.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'flip_coin' follows a clear verb_noun pattern.
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.
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
Related MCP Connectors
Fair, reproducible randomness for agents: dice, coins, integers, list picks, shuffles, with seeds.
Fair, reproducible randomness for agents: dice, coins, integers, list picks, shuffles, with seeds.
Fair, reproducible randomness for agents: dice, coins, integers, list picks, shuffles, with seeds.
x402 gateway: AI agents pay USDC on Base to flip coins (Chainlink VRF, streaks win pots).
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables 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.32MIT
- FlicenseNot gradedqualityDmaintenanceProvides 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-
- FlicenseNot gradedqualityDmaintenanceProvides true random generation tools for AI agents, including coin flip, dice roller, random numbers, and wheel of fortune, enabling decisions and TTRPG sessions.-
- AlicenseNot gradedqualityBmaintenanceEnables 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