Swift Tarot MCP Server
@junebash
Swift Tarot MCP Server について
A Swift-based MCP (Model Context Protocol) server for tarot card readings
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Swift Tarot MCP Server?
Swift Tarot MCP Server is a Model Context Protocol (MCP) server that provides tarot card reading functionality for AI assistants. It allows AI agents to draw tarot cards, perform multi-card readings, and access the complete 78‑card deck. The server is built in Swift and uses seeded random number generation for more reliable randomness than typical LLM behavior.
How to use Swift Tarot MCP Server?
Build and install the server using Swift 5.9+ on macOS 13.0+, then configure it as an MCP tool in Claude Desktop by adding the command swift-tarot-MCP to the claude_desktop_config.json file. After restarting Claude, ask Claude to draw cards or show the deck using natural language (e.g., “Draw me 5 tarot cards”).
Key features of Swift Tarot MCP Server
- Draw 1 to 78 tarot cards in a single request
- View all 78 cards in the traditional deck
- Fetch base64‑encoded images for tarot cards
- Uses seeded random number generation for deterministic testing
- Comprehensive input validation with proper error handling
Use cases of Swift Tarot MCP Server
- AI assistants that provide daily tarot readings to users
- Interactive storytelling or role‑playing with symbolic card draws
- Testing and debugging MCP tools with deterministic card outputs
- Educational apps that display full deck information and card imagery
FAQ from Swift Tarot MCP Server
What dependencies are required?
Swift 5.9 or later and macOS 13.0 or later are required.
How do I draw tarot cards?
Ask Claude (or your MCP client) to draw cards using the draw_cards tool. You can specify a count between 1 and 78 (default: 1).
Can I see images for the cards?
Yes, use the fetch_images tool with an array of tarot card URIs to receive base64‑encoded images.
How does the server handle randomness?
The server uses seeded random number generation, which provides deterministic, testable results while being more reliable than LLM‑inherent randomness.
What transport does the server use?
The server communicates over stdio transport and is configured as a command‑line MCP tool. No authentication or network setup is required.
「その他」の他のコンテンツ
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
コメント