Tarot MCP Server by RoxyAPI

Custom spread builder - Configurable tarot spread API

post_tarot_spreads_custom

Read-only

Build and perform your own custom tarot spread with personalized positions and interpretations (1-10 cards). This flexible endpoint lets you create unique spread layouts for any purpose: define your own position names, meanings, and card count to match your specific needs or therapeutic framework. Perfect for therapists using tarot in counseling, coaches creating signature spreads, app developers building custom reading features, spiritual practitioners with proprietary methods, or anyone wanting to design specialized layouts beyond traditional spreads. Create spreads for specific themes like chakra readings (7 cards), lunar phases (8 cards), elements (4 cards), goals setting (any count), shadow work, inner child healing, decision matrices, or creative problem-solving. Each position requires a name and interpretation, so you define what each card position represents in your reading. The API draws the exact number of cards you specify and maps them to your custom positions. No pre-generated summary is provided, so you interpret the reading based on your framework. Ideal for innovative tarot apps, therapeutic tools, personal development platforms, spiritual coaching services, or experimental divination methods. Maximum 10 positions to maintain reading clarity and practical interpretation time.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lang`	No	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.	en
`seed`	No	Optional seed for reproducible results. Same seed with the same positions produces identical card draws for consistent divination.
`compact`	No	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.
`question`	No	Optional querent question to focus the custom tarot reading. Provides context for position-specific interpretations.
`positions`	Yes	Array of 1-10 custom position definitions for your tarot spread. Each position gets one drawn card with a position-specific interpretation.
`spreadName`	No	Optional name for your custom tarot spread layout. Used as the spread identifier in the response.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No
`spread`	Yes
`question`	No
`positions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 20, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "positions": {
+      "items": {
+        "properties": {
+          "card": {
+            "properties": {
+              "arcana": {
+                "enum": [
+                  "major",
+                  "minor"
+                ],
+                "type": "string"
+              },
+              "career": {
+                "type": "string"
+              },
+              "finances": {
+                "type": "string"
+              },
+              "health": {
+                "type": "string"
+              },
+              "id": {
+                "type": "string"
+              },
+              "imageUrl": {
+                "type": "string"
+              },
+              "keywords": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "love": {
+                "type": "string"
+              },
+              "meaning": {
+                "type": "string"
+              },
+              "name": {
+                "type": "string"
+              },
+              "number": {
+                "type": "number"
+              },
+              "position": {
+                "type": "number"
+              },
+              "reversed": {
+                "type": "boolean"
+              },
+              "spirituality": {
+                "type": "string"
+              },
+              "suit": {
+                "enum": [
+                  "cups",
+                  "wands",
+                  "swords",
+                  "pentacles"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "id",
+              "name",
+              "arcana",
+              "position",
+              "reversed",
+              "keywords",
+              "meaning",
+              "imageUrl"
+            ],
+            "type": "object"
+          },
+          "interpretation": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "position": {
+            "type": "number"
+          }
+        },
+        "required": [
+          "position",
+          "name",
+          "interpretation",
+          "card"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "question": {
+      "type": "string"
+    },
+    "seed": {
+      "type": "string"
+    },
+    "spread": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "spread",
+    "positions"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedAug 25, 2026

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"
+]

Changed2 schema fields changedAug 17, 2026

addedInput schema / examples

Added value: +[
+  {
+    "positions": [
+      {
+        "interpretation": "What is really going on",
+        "name": "Core Issue"
+      },
+      {
+        "interpretation": "What you cannot see",
+        "name": "Hidden Factor"
+      },
+      {
+        "interpretation": "What to do next",
+        "name": "Best Action"
+      }
+    ]
+  }
+]

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."

Changed2 schema fields changedAug 2, 2026

changedInput schema / properties / question / example

Previous value: -"Optional question"New value: +"How do I move forward with this project?"

changedInput schema / properties / seed / example

Previous value: -"optional-seed"New value: +"reading-2f9c1a"

Changed1 schema field changedJul 22, 2026

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."

Changed1 schema field changedJul 22, 2026

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"
+}

First observedJul 8, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already state readOnlyHint=true and destructiveHint=false, but the description adds valuable behavioral details: 'The API draws the exact number of cards you specify and maps them to your custom positions,' 'No pre-generated summary is provided, so you interpret the reading based on your framework,' and 'Maximum 10 positions to maintain reading clarity.' These insights go beyond the structured annotations and set expectations for what the tool does not do.

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

Conciseness2/5

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

The description is far too long and includes promotional language that does not aid tool selection or invocation, such as lists of use cases ('chakra readings, lunar phases, elements...') and repetitive audience descriptions ('therapists using tarot in counseling, coaches creating signature spreads...'). The core information is diluted by many non-essential sentences; a concise version stating 'create custom spreads with user-defined position names and interpretations' would suffice.

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

Completeness4/5

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

Given the rich input schema (100% coverage), output schema, and annotations, the description is mostly complete: it explains the custom spread concept, the mapping of cards to positions, the absence of a pre-generated summary, and the 10-position limit. It falls slightly short on explicit comparison to sibling tools, but overall an agent can correctly invoke the tool with the provided information.

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

Parameters3/5

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

The input schema has 100% description coverage for all 6 parameters, including nested properties of 'positions'. The description does not add new parameter-level semantics beyond what the schema already provides—it repeats the idea that each position has a name and interpretation, and mentions the 1-10 card count, which is already in the schema's minItems/maxItems. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 states a specific verb and resource: 'Build and perform your own custom tarot spread with personalized positions and interpretations (1-10 cards).' It clearly distinguishes this from sibling tools by emphasizing the customizable positions and 'beyond traditional spreads' context. The title and description align, making the tool's purpose unmistakable.

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?

The description provides clear context for when this tool is appropriate: 'Perfect for therapists... coaches... app developers...' and 'anyone wanting to design specialized layouts beyond traditional spreads.' It implies use for custom layouts but does not explicitly name alternatives or state when not to use it (e.g., 'use a dedicated spread endpoint for standard layouts'), so it lacks explicit exclusions.

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 tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?