Tarotoo Tarot MCP Server
Enables AI assistants to look up tarot card meanings, search cards by keyword, draw random cards, and get yes/no answers for all 78 Rider-Waite-Smith cards with upright and reversed interpretations.
README
Tarotoo Tarot MCP Server
A Model Context Protocol server that gives AI assistants — Claude, ChatGPT, Cursor, and any other MCP client — live access to the Tarotoo tarot card meanings dataset: all 78 cards in the Rider–Waite–Smith tradition, with upright and reversed meanings and keywords, upright and reversed love, career, mood and spiritual contexts, planet and zodiac associations, and upright and reversed yes/no values.
Published by Tarotoo: these are the same card meanings that ground the AI readings on Tarotoo.com.
Quick start
Requires Node.js ≥ 18. No installation needed — clients run it via npx.
Claude Code
claude mcp add tarotoo-tarot -- npx -y tarotoo-mcp-server
Claude Desktop — add to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"tarotoo-tarot": {
"command": "npx",
"args": ["-y", "tarotoo-mcp-server"]
}
}
}
Cursor / Windsurf / other MCP clients — same command/args pair in the client's MCP settings.
MCP registry — listed as io.github.Tarotoo-com/tarotoo-mcp-server, so registry-aware clients can discover and install it directly.
Then ask your assistant things like "what does the Three of Swords mean for my career?" or "draw three cards for me" — it will call the tools below.
Tools
| Tool | Arguments | Returns |
|---|---|---|
get_card_meaning |
name (string) |
Full record for one card — meanings, keywords, love/career/mood/spiritual (upright and reversed), planet, zodiac, yes/no. Name matching is forgiving ("fool" → The Fool) |
list_cards |
arcana? (major/minor), suit? (wands/cups/swords/pentacles) |
Card names, optionally filtered |
search_cards |
query (string), limit? (1–78, default 10) |
Cards matching a theme or keyword, best match first — e.g. "heartbreak" → Three of Swords |
yes_no_answer |
name (string) |
The card's yes/no/maybe value with its upright meaning as justification |
draw_cards |
count? (1–10, default 1), allow_reversed? (boolean) |
Random distinct cards with orientation-appropriate meanings — for generating spreads |
Example
tools/call get_card_meaning {"name": "the star"}
{
"name": "The Star",
"arcana": "major",
"element": "Air",
"planet": "Saturn",
"zodiac": "Aquarius",
"yes_no": "yes",
"yes_no_reversed": "no",
"keywords_upright": ["hope", "renewal", "healing", "inspiration", "faith"],
"meaning_upright": "Hope, renewal, healing, inspiration, faith.",
"love": "hope in love, emotional healing, renewed trust, an inspiring connection",
"love_reversed": "lost faith, discouragement, disconnection, dimmed hope"
}
Each card carries both upright and reversed values for keywords, meaning, love, career, mood, spiritual, and yes/no. The example above is abbreviated.
Run from source
git clone https://github.com/Tarotoo-com/tarotoo-mcp-server.git
cd tarotoo-mcp-server
npm install
npm test # 8-check smoke test: full MCP session over stdio
node server.js # stdio transport
Dataset
The embedded data/cards.json is built from tarotoo-tarot-dataset (MIT), which is also available on Hugging Face, Kaggle, npm, and PyPI, with citable DOIs: 10.5281/zenodo.21285777 (dataset + dataset paper; concept DOI, always latest) and 10.5281/zenodo.21268290 (full repository/archive: dataset, source files, build scripts, automated validation, software packages, documentation; concept DOI, always latest).
Interpretations were created by Tarotoo within the Rider–Waite–Smith tradition, drawing on established sources (A. E. Waite's The Pictorial Key to the Tarot, 1911; attributions per the Golden Dawn's Book T).
License
Code and dataset: MIT. Attribution to Tarotoo (tarotoo.com) is appreciated.
Intended Use
This dataset is intended for educational, research, creative, entertainment, and self-reflection purposes. It should not be used as a substitute for medical, legal, financial, mental-health, or other professional advice.
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。