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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.