mcp-dice
mcp-dice: サイコロを振るためのMCPサーバー
大規模言語モデル(LLM)がサイコロを振れるようにするモデルコンテキストプロトコル(MCP)サーバー。標準的なサイコロ表記(例: 1d20 )を受け付け、個々の出目とその合計を返します。
特徴
標準的なサイコロ表記法
3d6サポート(例:1d20``2d8+1)個々のロールと合計の両方を返します
Claude Desktopとの簡単な統合
デバッグ用のMCP Inspectorと互換性あり
Related MCP server: Globalping
インストール
Smithery経由でインストール
Smithery経由で Claude Desktop 用の Dice Roller を自動的にインストールするには:
npx @smithery/cli install mcp-dice --client claudeuvを利用できるようにします: https://docs.astral.sh/uv/getting-started/installation/
使用法
基本的なコマンドラインの使用法
# Using uvx
uvx mcp-dice入力形式
サーバーは、 notationフィールドを持つ JSON オブジェクトを受け入れます。
{
"notation": "2d6+3"
}応答例:
{
"rolls": [
3,
1
],
"sum": 4,
"modifier": 3,
"total": 7,
"notation": "2d6+3",
"timestamp": "2024-12-03T16:36:38.926452"
}クロードデスクトップ構成
位置
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%/Claude/claude_desktop_config.json
例
{
"mcpServers": {
"dice": {
"command": "uvx",
"args": ["mcp-dice"]
}
}
}{
"mcpServers": {
"dice": {
"command": "wsl",
"args": [
"-e",
"zsh",
"-lc",
"uvx mcp-dice"
]
}
}
}注: zshログイン シェルに置き換えます。
開発とデバッグ
開発依存関係のインストール
# Clone the repository
git clone https://github.com/yourusername/mcp-dice
cd mcp-dice
# Install development dependencies
uv pip install -e ".[dev]"テストの実行
uv run pytestMCPインスペクターの使用
MCP Inspectorは、MCPサーバーのデバッグに役立つツールです。npmを使ってインストールして実行してください。
npx @modelcontextprotocol/inspector uvx mcp-dice開発のためのClaudeデスクトップ構成
{
"mcpServers": {
"dice": {
"command": "uv",
"args": [
"run",
"--directory",
"path/to/mcp-dice-repo",
"mcp-dice"
]
}
}
}注: path/to/mcp-dice-repoファイルシステム上のリポジトリへのパスに置き換えます。
{
"mcpServers": {
"dice": {
"command": "wsl",
"args": [
"-e",
"zsh",
"-lc",
"uv run --directory path/to/mcp-dice-repo mcp-dice"
]
}
}
}注: zshログインシェルに置き換えてください。また、 path/to/mcp-dice-repo WSLファイルシステム上のリポジトリへのパスに置き換えてください。
Available Tools
1 toolroll_diceA
Roll dice using standard notation (e.g., '2d6+3', '1d20-2')
| Name | Required | Description | Default |
|---|---|---|---|
| notation | Yes | Dice notation (e.g., '2d6+3', '1d20-2') |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It describes the action but lacks behavioral details such as whether this is a deterministic or random process, any rate limits, or what the output format might be. The description is minimal and does not compensate for the absence of annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the purpose and provides clear examples. There is no wasted information, making it appropriately concise and well-structured for its purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter, no output schema, no annotations), the description is adequate but has gaps. It explains the input but lacks details on output or behavioral context, making it minimally viable but not fully complete for an agent to understand all aspects without additional inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents the single parameter 'notation' with a description and pattern. The description adds minimal value by restating the parameter concept with examples, aligning with the baseline score when schema coverage is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Roll dice') and resource ('using standard notation'), with examples provided. It precisely defines what the tool does without being tautological, and since there are no sibling tools, no differentiation is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by providing examples of dice notation, but it does not explicitly state when to use this tool versus alternatives. Since there are no sibling tools, no explicit alternatives are mentioned, leaving usage context somewhat implied rather than fully guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
roll_dice
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'roll_dice' has a clearly distinct purpose that cannot be confused with any other tool in this set.
The naming follows a consistent verb_noun pattern with 'roll_dice', and since there is only one tool, there is no inconsistency to evaluate. The naming is clear and predictable for this single-tool server.
A single tool is generally too few for most server purposes, as it limits functionality and can feel thin. For a dice-rolling server, while the core operation is covered, additional tools like rolling multiple dice types or retrieving roll history could enhance completeness, making the count borderline inappropriate.
The tool covers the basic dice-rolling functionality well, but there are notable gaps. For example, there are no tools for listing available dice types, saving roll results, or performing statistical analysis on rolls, which could be expected in a more comprehensive dice-rolling domain.
Maintenance
Related MCP Connectors
MCP server for AI dialogue using various LLM models via AceDataCloud
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2
Related MCP Servers
- AlicenseBqualityCmaintenanceAn MCP server that provides LLMs access to other LLMs428 npm79MIT

Globalpingofficial
FlicenseNot gradedqualityBmaintenanceRemote MCP server that gives LLMs access to run network commands64-- AlicenseNot gradedqualityCmaintenanceAn MCP server that enables AI agents to act as dynamic dungeon masters for text-based RPGs with dynamically generated rule systems and comprehensive game state management.8 npm12MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server enabling AI agents to autonomously play D\&D as players and Dungeon Masters, with real dice rolls and full campaign management.2MIT