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.
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.