Skip to main content
Glama

Tarot MCP Server by RoxyAPI

by com.roxyapi

Draw tarot cards - Seeded tarot draw API

post_tarot_draw
Read-only

Draw 1-78 tarot cards from the complete Rider-Waite-Smith deck with seeded reproducibility for consistent personalized readings. Provide an optional seed string (like "user123-2025-12-27" or "readingId") to ensure the same seed always returns identical cards in the exact same order, which is essential for daily tarot features, personalized user experiences, shareable readings, or reproducible testing. Omit seed for true random draws each time. Control card reversals (upright vs reversed or inverted orientations, where reversed cards provide alternative meanings when drawn upside down) and duplicates (traditional deck draws each of 78 cards once, or oracle-style allows repeating same card). Each drawn card includes position number, reversal state (boolean), keywords for quick interpretation, full meaning text (400+ words), authentic Rider-Waite imagery, and card metadata. Perfect for custom spread builders, random card generators, automated tarot reading platforms, daily card features, meditation apps, journaling prompts, divination tools, and any application requiring reproducible or random tarot draws from the industry-standard 78-card deck (22 Major Arcana spiritual lessons + 56 Minor Arcana practical guidance across 4 suits).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNoResponse language (BCP 47). Supported: en, tr, de, es, hi, pt, fr, ru, zh-Hans, zh-Hant. Defaults to en. Coverage varies by domain, and a field with no translation in the requested language returns English.en
seedNoOptional seed for reproducible results. Same seed = same cards in same order. Use format like "userId-date" for daily consistency, or "readingId" for shareable readings. Omit for true randomness.
countYesNumber of cards to draw (1-78). Common values: 1 for daily card, 3 for past-present-future, 5 for relationship spread, 10 for Celtic Cross. Drawing 78 returns the entire shuffled deck.
compactNoSet true for the same data in a compact shape: arrays of same-shaped objects arrive columnar as {"__cols":[names],"__rows":[[values]]}. Lossless, typically 40 to 52 percent fewer tokens.
allowReversalsNoWhether cards can appear reversed (upside down). Reversed cards have different meanings. Set false for upright-only readings. Default: true (50% chance of reversal per card).
allowDuplicatesNoWhether same card can be drawn multiple times. Set false for traditional deck behavior (each card drawn only once). Set true for statistical analysis or oracle-style readings. Default: false.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / lang / description
      Previous value: -"Response language (ISO 639-1). Supported: en, tr, de, es, hi, pt, fr, ru. Defaults to en. Languages without translations yet return English."New value: +"Response language (BCP 47). Supported: en, tr, de, es, hi, pt, fr, ru, zh-Hans, zh-Hant. Defaults to en. Coverage varies by domain, and a field with no translation in the requested language returns English."
    • changedInput schema / properties / lang / enum
      Previous value: -[
-  "en",
-  "tr",
-  "de",
-  "es",
-  "hi",
-  "pt",
-  "fr",
-  "ru"
-]New value: +[
+  "en",
+  "tr",
+  "de",
+  "es",
+  "hi",
+  "pt",
+  "fr",
+  "ru",
+  "zh-Hans",
+  "zh-Hant"
+]
  2. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "count": 3
+  }
+]
    • changedInput schema / properties / compact / description
      Previous value: -"Set true to receive the exact same data in a token-optimized shape that is cheaper for you to read: whitespace is stripped and every array of same-shaped objects is encoded columnar as {\"__cols\":[field names],\"__rows\":[[values]]}, so each field name is sent once instead of once per row. Fully lossless (no field or value is dropped or changed) and typically 40 to 52 percent fewer tokens on large results. Prefer true whenever token or inference cost matters. Default false returns standard indented JSON."New value: +"Set true for the same data in a compact shape: arrays of same-shaped objects arrive columnar as {\"__cols\":[names],\"__rows\":[[values]]}. Lossless, typically 40 to 52 percent fewer tokens."
  3. Changed1 schema field changed
    • changedInput schema / properties / compact / description
      Previous value: -"Return the same data in a token-optimized compact shape (minified, with same-shaped arrays encoded columnar) to reduce LLM token cost. Lossless: no fields are dropped. Default false."New value: +"Set true to receive the exact same data in a token-optimized shape that is cheaper for you to read: whitespace is stripped and every array of same-shaped objects is encoded columnar as {\"__cols\":[field names],\"__rows\":[[values]]}, so each field name is sent once instead of once per row. Fully lossless (no field or value is dropped or changed) and typically 40 to 52 percent fewer tokens on large results. Prefer true whenever token or inference cost matters. Default false returns standard indented JSON."
  4. Changed1 schema field changed
    • addedInput schema / properties / compact
      Added value: +{
+  "default": false,
+  "description": "Return the same data in a token-optimized compact shape (minified, with same-shaped arrays encoded columnar) to reduce LLM token cost. Lossless: no fields are dropped. Default false.",
+  "type": "boolean"
+}
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only/non-destructive, and the description adds meaningful behavioral detail: deterministic same-seed ordering, 50% default reversal probability, traditional no-duplicate deck behavior, compact lossless shape, and drawing 78 returning the entire shuffled deck. No statements contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core draw and seed behavior, but the latter portion is verbose and includes marketing-style lists such as 'perfect for custom spread builders' and 'authentic Rider-Waite imagery,' plus an arcana breakdown that adds little for an agent deciding how to invoke the tool. The useful behavioral content could be delivered in roughly half the words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter tool with no output schema, the description tells an agent exactly what each returned card contains—position, reversal state, keywords, 400+ word meaning, imagery, and metadata—and explains all major behavioral toggles (seed, reversals, duplicates, compact). It is complete enough to select parameters and interpret the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with per-parameter descriptions for all six parameters. The prose adds value on top—seed format guidance, common count values (1 daily, 3 past-present-future, 5 relationship, 10 Celtic Cross), default reversal probability, and oracle-style duplicate semantics—so it earns more than the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: draw 1-78 tarot cards from the complete Rider-Waite-Smith deck with seeded reproducibility. It clearly distinguishes the core capability from sibling spread/daily/yes-no tools by emphasizing custom draw mechanics and deterministic seed behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit operational direction around seeding: provide a seed for reproducible readings, omit for true randomness, set allowReversals=false for upright-only, and allowDuplicates=true for oracle-style readings. It identifies this tool as suitable for custom spread builders and random card generators, implying when fixed-spread siblings would be more appropriate, though it does not name those alternatives explicitly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Tarot MCP Server by RoxyAPI toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: deck list/detail, daily draws, generic draws, four named spreads, custom spreads, and yes/no readings. Even the overlapping draw endpoints are distinguishable by their specific use cases.

Naming Consistency5/5

All tool names consistently follow a snake_case verb_tarot_resource pattern, which makes the toolset predictable and easy to navigate. The only minor oddity is get_tarot_cards_id, but it does not break the overall convention.

Tool Count5/5

Ten tools is an ideal size for a tarot API: two reference tools, one daily draw, one generic draw, four fixed spreads, one custom spread, and one yes/no tool. Each tool earns its place without overlap or bloat.

Completeness5/5

The surface covers the full tarot domain: browsing cards, retrieving detailed card interpretations, drawing cards, multiple popular spread types, custom spreads, and targeted yes/no guidance. There are no obvious dead ends or critical missing workflows.

Resources