Magic 8-Ball MCP Server
A demonstration MCP server built with TypeScript and Bun that implements a classic Magic 8-Ball oracle. It enables users to ask yes/no questions, use prompt templates, and access the full list of classic responses.
README
Magic 8-Ball MCP Server
A demo Model Context Protocol server that implements a classic Magic 8-Ball oracle. Built with TypeScript and Bun.
What's Inside
| MCP Primitive | Name | Description |
|---|---|---|
| Tool | shake |
Ask a yes/no question, get a random 8-Ball answer |
| Prompt | ask-the-8-ball |
Reusable prompt template for consulting the oracle |
| Resource | magic-8-ball://responses |
The complete list of 20 classic responses |
Prerequisites
- Bun v1.0+
- Claude Desktop (for installing the
.mcpbbundle)
Getting Started
# Install dependencies
bun install
# Run the server directly (stdio transport)
bun run start
Testing with MCP Inspector
The MCP Inspector provides a browser UI for interacting with your server.
bun run inspect
This opens http://localhost:6274 where you can:
- Tools — Call
shakewith a question and see random 8-Ball responses - Prompts — Get the
ask-the-8-ballprompt template with a question filled in - Resources — Read
magic-8-ball://responsesto see all 20 classic answers
Building & Packaging for Claude Desktop
1. Build
Compile TypeScript to JavaScript so the bundle can run with Node.js (which ships with Claude Desktop):
bun run build
This creates dist/index.js — a single-file bundle with all dependencies included.
2. Create the manifest
If you haven't already, initialize the MCPB manifest:
bunx @anthropic-ai/mcpb init
A manifest.json is already included in this repo. You can validate it:
bunx @anthropic-ai/mcpb validate manifest.json
3. Pack
bunx @anthropic-ai/mcpb pack .
This creates a .mcpb file (e.g., magic-8-ball-mcp-1.0.0.mcpb).
4. Install in Claude Desktop
Double-click the .mcpb file (or open it with Claude Desktop). Claude will show an installation dialog — click Install and the Magic 8-Ball tools will be available in your conversations.
Project Structure
bun-demo-mcp/
├── .claude/
│ └── CLAUDE.md # Claude Code project instructions
├── dist/
│ └── index.js # Compiled bundle (generated)
├── src/
│ ├── index.ts # MCP server (tool + prompt + resource)
│ └── responses.ts
├── bun.lock
├── manifest.json # MCPB bundle manifest
├── package.json
├── README.md
└── tsconfig.json
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。