StockCake
Search millions of CC0 public-domain AI images: previews, dimensions, provenance, license.
¿Debería usar esto?
Calidad y seguridad
A
Hallazgos (1)
- LOWTool 'get_license_info' description lacks action verben get_license_info
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
~8,251Tokens (definiciones de herramientas)
~7.4 KBTamaño de respuesta típico
Impacto significativo en la atención (6.45% del contexto de 128k)
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"stockcake": {
"url": "https://stockcake.com/api/mcp"
}
}
}Puntos de conexión remotos
https://stockcake.com/api/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (12)
🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢search_images(query, orientation, type, color, mood, ...)
Natural-language search over StockCake's catalog. total_results is the total number of matches across the whole catalog, not just this page. refinements lists exact mood/style values available for this query. Start with a short query; when total_results is small or off-target, retry with fewer keywords or different phrasing.
Esquema de entrada
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 300,
"description": "Short subject, 2–5 words (e.g. 'red vintage rocket'). Long sentences hurt recall: start short, add one qualifier at a time; if results are thin, drop keywords or rephrase."
},
"orientation": {
"type": "string",
"enum": [
"landscape",
"portrait",
"square"
]
},
"type": {
"type": "string",
"enum": [
"photos",
"illustrations",
"digital-art",
"3d"
]
},
"color": {
"description": "Dominant color, e.g. a hex value like #ff0000",
"type": "string",
"maxLength": 30
},
"mood": {
"description": "Exact facet value — pick one from refinements.mood of a previous search_images result",
"type": "string",
"maxLength": 50
},
"style": {
"description": "Exact facet value — pick one from refinements.style of a previous search_images result",
"type": "string",
"maxLength": 50
},
"page": {
"description": "Page number, 1-5",
"type": "integer",
"minimum": 1,
"maximum": 5
},
"limit": {
"description": "Results to return, 1-12 (default 12). Ask for fewer to save tokens.",
"type": "integer",
"minimum": 1,
"maximum": 12
},
"locale": {
"description": "Site locale for the user (default en). Titles and page links are localized; descriptions are English.",
"type": "string",
"enum": [
"en",
"de",
"es",
"fa",
"fr",
"it",
"ja",
"pt"
]
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"query",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "number"
},
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"preview_url": {
"type": "string"
},
"page_url": {
"type": "string"
},
"aspect_ratio": {
"type": "string",
"description": "e.g. \"16:9\", \"9:16\", \"1:1\""
},
"dimensions": {
"anyOf": [
{
"type": "object",
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"required": [
"width",
"height"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Full-resolution pixel size; null when unknown"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"title",
"preview_url",
"page_url",
"aspect_ratio",
"dimensions",
"tags"
],
"additionalProperties": false
}
},
"page": {
"type": "number"
},
"total_results": {
"type": "number"
},
"total_pages": {
"type": "number"
},
"has_more": {
"type": "boolean"
},
"license_note": {
"type": "string"
},
"refinements": {
"description": "Exact mood/style facet values available for this query — pass one back as `mood` / `style` to narrow",
"type": "object",
"properties": {
"mood": {
"type": "array",
"items": {
"type": "string"
}
},
"style": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"mood",
"style"
],
"additionalProperties": false
}
},
"required": [
"results",
"page",
"total_results",
"total_pages",
"has_more",
"license_note"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢find_similar_images(id, page, limit, locale, context, ...)
Find images visually similar to a given StockCake image id (from search_images results). total_results is the number of similar results returned on this page, not a catalog-wide count.
Esquema de entrada
{
"type": "object",
"properties": {
"id": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991,
"description": "Numeric image id from a previous result"
},
"page": {
"description": "Page number, 1-5",
"type": "integer",
"minimum": 1,
"maximum": 5
},
"limit": {
"description": "Results to return, 1-12 (default 12). Ask for fewer to save tokens.",
"type": "integer",
"minimum": 1,
"maximum": 12
},
"locale": {
"description": "Site locale for the user (default en). Titles and page links are localized; descriptions are English.",
"type": "string",
"enum": [
"en",
"de",
"es",
"fa",
"fr",
"it",
"ja",
"pt"
]
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"id",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "number"
},
"title": {
"type": "string"
},
"description": {
"type": "string"
},
"preview_url": {
"type": "string"
},
"page_url": {
"type": "string"
},
"aspect_ratio": {
"type": "string",
"description": "e.g. \"16:9\", \"9:16\", \"1:1\""
},
"dimensions": {
"anyOf": [
{
"type": "object",
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"required": [
"width",
"height"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Full-resolution pixel size; null when unknown"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"id",
"title",
"preview_url",
"page_url",
"aspect_ratio",
"dimensions",
"tags"
],
"additionalProperties": false
}
},
"page": {
"type": "number"
},
"total_results": {
"type": "number"
},
"total_pages": {
"type": "number"
},
"has_more": {
"type": "boolean"
},
"license_note": {
"type": "string"
},
"refinements": {
"description": "Exact mood/style facet values available for this query — pass one back as `mood` / `style` to narrow",
"type": "object",
"properties": {
"mood": {
"type": "array",
"items": {
"type": "string"
}
},
"style": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"mood",
"style"
],
"additionalProperties": false
}
},
"required": [
"results",
"page",
"total_results",
"total_pages",
"has_more",
"license_note"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_image(id, include_preview, locale, context, llm_model, ...)
Fetch one image with full metadata: an inline preview the model can see (unless include_preview is false), real pixel dimensions, AI-generation provenance (prompt, dates, style), license details, and attribution snippets.
Esquema de entrada
{
"type": "object",
"properties": {
"id": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 2147483647
},
{
"type": "string",
"minLength": 4,
"maxLength": 64
}
],
"description": "Numeric image id (from search results) or the image's CDN uuid"
},
"include_preview": {
"description": "Default true. Set false to skip the inline preview image and save tokens.",
"type": "boolean"
},
"locale": {
"description": "Site locale for the user (default en). Titles and page links are localized; descriptions are English.",
"type": "string",
"enum": [
"en",
"de",
"es",
"fa",
"fr",
"it",
"ja",
"pt"
]
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"id",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"properties": {
"id": {
"type": "number"
},
"title": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
},
"dimensions": {
"anyOf": [
{
"type": "object",
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"required": [
"width",
"height"
],
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Full-resolution pixel size; null when unknown"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"provenance": {
"type": "object",
"properties": {
"ai_generated": {
"type": "boolean",
"const": true
},
"prompt": {
"type": [
"string",
"null"
]
},
"style": {
"type": [
"string",
"null"
]
},
"generated_at": {
"type": [
"string",
"null"
]
},
"published_at": {
"type": [
"string",
"null"
]
},
"descriptive_attributes": {
"anyOf": [
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
{
"type": "null"
}
]
}
},
"required": [
"ai_generated",
"prompt",
"style",
"generated_at",
"published_at",
"descriptive_attributes"
],
"additionalProperties": false
},
"license": {
"type": "object",
"properties": {
"license": {
"type": "string"
},
"license_url": {
"type": "string"
},
"public_domain": {
"type": "boolean"
},
"commercial_use": {
"type": "boolean"
},
"attribution_required": {
"type": "boolean"
},
"restrictions": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"license",
"license_url",
"public_domain",
"commercial_use",
"attribution_required",
"restrictions"
],
"additionalProperties": false
},
"page_url": {
"type": "string"
},
"preview_url": {
"type": "string"
},
"attribution": {
"type": "object",
"properties": {
"markdown": {
"type": "string"
},
"html": {
"type": "string"
},
"plain": {
"type": "string"
}
},
"required": [
"markdown",
"html",
"plain"
],
"additionalProperties": false
}
},
"required": [
"id",
"title",
"description",
"dimensions",
"tags",
"provenance",
"license",
"page_url",
"preview_url",
"attribution"
],
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}🟢get_license_info(context, llm_model, conversation_id)
License and usage terms for all StockCake images (site-wide CC0 / public domain).
Esquema de entrada
{
"type": "object",
"properties": {
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_account(context, llm_model, conversation_id)
The signed-in user's plan, credit balance (free / subscription / purchased), next resets, download quality and output formats. Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"plan": {
"type": "string"
},
"tier": {
"type": [
"string",
"null"
]
},
"is_entitled": {
"type": "boolean"
},
"balance": {
"type": "object",
"properties": {
"total": {
"type": "number"
},
"free": {
"type": "number"
},
"subscription": {
"type": "number"
},
"purchased": {
"type": "number"
}
},
"required": [
"total",
"free",
"subscription",
"purchased"
],
"additionalProperties": false
},
"next_reset": {
"type": "object",
"properties": {
"free": {
"type": [
"string",
"null"
]
},
"subscription": {
"type": [
"string",
"null"
]
}
},
"required": [
"free",
"subscription"
],
"additionalProperties": false
},
"max_download_multiplier": {
"type": "number"
},
"formats": {
"type": "array",
"items": {
"type": "string"
}
},
"upgrade_url": {
"type": "string"
}
},
"required": [
"plan",
"tier",
"is_entitled",
"balance",
"next_reset",
"max_download_multiplier",
"formats",
"upgrade_url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟢list_models(kind, context, llm_model, conversation_id)
Image and video models available to generate_image / create_video with the credit price of every tier. Free-credit models are flagged; video is priced per second. Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"kind": {
"description": "Return only one catalog",
"type": "string",
"enum": [
"image",
"video"
]
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"image": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"provider": {
"type": "string"
},
"description": {
"type": "string"
},
"default": {
"type": "boolean"
},
"free": {
"type": "boolean"
},
"default_tier": {
"type": "string"
},
"tiers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"label": {
"type": "string"
},
"credits": {
"type": "number"
},
"resolution": {
"type": "string"
}
},
"required": [
"key",
"label",
"credits"
],
"additionalProperties": false
}
},
"supports_references": {
"type": "boolean"
},
"max_references": {
"type": "number"
}
},
"required": [
"id",
"name",
"provider",
"description",
"default",
"free",
"default_tier",
"tiers",
"supports_references",
"max_references"
],
"additionalProperties": false
}
},
"video": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"provider": {
"type": "string"
},
"description": {
"type": "string"
},
"default": {
"type": "boolean"
},
"default_tier": {
"type": "string"
},
"tiers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"key": {
"type": "string"
},
"resolution": {
"type": "string"
},
"audio": {
"type": "boolean"
},
"credits_per_second": {
"type": "number"
}
},
"required": [
"key",
"resolution",
"audio",
"credits_per_second"
],
"additionalProperties": false
}
},
"durations": {
"type": "array",
"items": {
"type": "number"
}
},
"default_duration": {
"type": "number"
},
"image_to_video": {
"type": "boolean"
},
"aspect_ratios": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
]
}
},
"required": [
"id",
"name",
"provider",
"description",
"default",
"default_tier",
"tiers",
"durations",
"default_duration",
"image_to_video",
"aspect_ratios"
],
"additionalProperties": false
}
}
},
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟢generate_image(prompt, model, tier, aspect_ratio, reference_images, ...)
Generate a new image from a prompt with one of StockCake's AI models (list_models). Charges credits; free credits cover the free models. Waits up to 45 s — a pending result carries a job_id for get_job. Optional reference images guide the composition (plan-capped). Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 2000
},
"model": {
"description": "Model id from list_models. Default: the site default for subscribers, the free model otherwise.",
"type": "string",
"maxLength": 64
},
"tier": {
"description": "Tier key from list_models (e.g. 1k, 2k, standard). Default: the model's default tier.",
"type": "string",
"maxLength": 16
},
"aspect_ratio": {
"type": "string",
"enum": [
"9:16",
"4:5",
"3:4",
"2:3",
"1:1",
"3:2",
"4:3",
"5:4",
"16:9"
]
},
"reference_images": {
"description": "Stock image ids or your own edited image ids used as references",
"maxItems": 9,
"type": "array",
"items": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"minLength": 1,
"maxLength": 64
}
],
"description": "A StockCake image id (from search_images), one of your own edited image ids (from a previous result), or a job_id. Never a URL."
}
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"prompt",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "completed"
},
"image": {
"type": "object",
"properties": {
"id": {
"description": "Edited image id — pass it to download_image or as an image reference",
"type": [
"number",
"null"
]
},
"url": {
"type": "string"
}
},
"required": [
"id",
"url"
],
"additionalProperties": false
},
"credits_charged": {
"type": "number"
}
},
"required": [
"job_id",
"status",
"image",
"credits_charged"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "pending"
},
"credits_charged": {
"type": "number"
},
"message": {
"type": "string"
}
},
"required": [
"job_id",
"status",
"credits_charged",
"message"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟢upscale_image(image, scale, context, llm_model, conversation_id)
Upscale a StockCake image or one of your edited images 2x, 4x or 8x (lossless PNG output). Plan quality caps apply; charges credits otherwise. Waits up to 45 s, then returns a job_id for get_job. Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"image": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"minLength": 1,
"maxLength": 64
}
],
"description": "A StockCake image id (from search_images), one of your own edited image ids (from a previous result), or a job_id. Never a URL."
},
"scale": {
"anyOf": [
{
"type": "number",
"const": 2
},
{
"type": "number",
"const": 4
},
{
"type": "number",
"const": 8
}
]
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"image",
"scale",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "completed"
},
"image": {
"type": "object",
"properties": {
"id": {
"description": "Edited image id — pass it to download_image or as an image reference",
"type": [
"number",
"null"
]
},
"url": {
"type": "string"
}
},
"required": [
"id",
"url"
],
"additionalProperties": false
},
"credits_charged": {
"type": "number"
}
},
"required": [
"job_id",
"status",
"image",
"credits_charged"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "pending"
},
"credits_charged": {
"type": "number"
},
"message": {
"type": "string"
}
},
"required": [
"job_id",
"status",
"credits_charged",
"message"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟡resize_image(image, aspect_ratio, prompt, context, llm_model, ...)
Change an image's aspect ratio by extending the canvas with AI (GPT Image 2.5) — the subject is kept, new area is generated. Charges credits. Waits up to 45 s, then returns a job_id for get_job. Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"image": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"minLength": 1,
"maxLength": 64
}
],
"description": "A StockCake image id (from search_images), one of your own edited image ids (from a previous result), or a job_id. Never a URL."
},
"aspect_ratio": {
"type": "string",
"enum": [
"9:16",
"4:5",
"3:4",
"2:3",
"1:1",
"3:2",
"4:3",
"5:4",
"16:9"
],
"description": "Target ratio"
},
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "What should fill the extended canvas, e.g. 'extend the sandy beach and sky; keep the subject unchanged, do not crop or stretch'"
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"image",
"aspect_ratio",
"prompt",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "completed"
},
"image": {
"type": "object",
"properties": {
"id": {
"description": "Edited image id — pass it to download_image or as an image reference",
"type": [
"number",
"null"
]
},
"url": {
"type": "string"
}
},
"required": [
"id",
"url"
],
"additionalProperties": false
},
"credits_charged": {
"type": "number"
}
},
"required": [
"job_id",
"status",
"image",
"credits_charged"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "pending"
},
"credits_charged": {
"type": "number"
},
"message": {
"type": "string"
}
},
"required": [
"job_id",
"status",
"credits_charged",
"message"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟡create_video(prompt, model, tier, duration_seconds, aspect_ratio, ...)
Generate a short video from a prompt and/or a start image with one of StockCake's video models (list_models). Priced per second of output; needs a plan. Video usually takes longer than 45 s: expect a pending result and poll get_job. Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"prompt": {
"description": "Required unless start_image is given",
"type": "string",
"maxLength": 2000
},
"model": {
"description": "Video model id from list_models (default: Veo 3.1 Fast)",
"type": "string",
"maxLength": 64
},
"tier": {
"description": "Tier key from list_models (e.g. 720p, 1080p, 720p-audio)",
"type": "string",
"maxLength": 24
},
"duration_seconds": {
"description": "Clip length; must be one of the model's durations",
"type": "integer",
"minimum": 1,
"maximum": 30
},
"aspect_ratio": {
"description": "Text-to-video only; a start image sets the ratio",
"type": "string",
"enum": [
"9:16",
"4:5",
"3:4",
"2:3",
"1:1",
"3:2",
"4:3",
"5:4",
"16:9"
]
},
"start_image": {
"description": "Animate from this image (stock id or your edited image id)",
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"minLength": 1,
"maxLength": 64
}
]
},
"negative_prompt": {
"type": "string",
"maxLength": 1000
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "completed"
},
"video": {
"type": "object",
"properties": {
"url": {
"type": "string"
},
"duration_seconds": {
"type": [
"number",
"null"
]
}
},
"required": [
"url",
"duration_seconds"
],
"additionalProperties": false
},
"credits_charged": {
"type": "number"
}
},
"required": [
"job_id",
"status",
"video",
"credits_charged"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"const": "pending"
},
"credits_charged": {
"type": "number"
},
"message": {
"type": "string"
}
},
"required": [
"job_id",
"status",
"credits_charged",
"message"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟢download_image(id, format, context, llm_model, conversation_id)
Full-resolution download link for a StockCake image (CC0) or one of your edited images. Unmetered — no credits. format "png" returns the lossless sibling when one exists (falls back to jpg). Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"id": {
"anyOf": [
{
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 9007199254740991
},
{
"type": "string",
"pattern": "^\\d+$"
}
],
"description": "Stock image id or your own edited image id"
},
"format": {
"description": "Default jpg (the original)",
"type": "string",
"enum": [
"jpg",
"png"
]
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"id",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"id": {
"type": "number"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"format": {
"type": "string"
},
"dimensions": {
"anyOf": [
{
"type": "object",
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"required": [
"width",
"height"
],
"additionalProperties": false
},
{
"type": "null"
}
]
},
"license": {
"type": "object",
"properties": {
"license": {
"type": "string"
},
"license_url": {
"type": "string"
},
"public_domain": {
"type": "boolean"
},
"commercial_use": {
"type": "boolean"
},
"attribution_required": {
"type": "boolean"
},
"restrictions": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"license",
"license_url",
"public_domain",
"commercial_use",
"attribution_required",
"restrictions"
],
"additionalProperties": false
},
"page_url": {
"type": "string"
}
},
"required": [
"id",
"title",
"url",
"format",
"dimensions",
"license",
"page_url"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}🟢get_job(job_id, context, llm_model, conversation_id)
Status and result of a generate_image / upscale_image / resize_image / create_video job you started (pending, completed with URLs, or error with refund state). Requires a free StockCake account (the host will prompt to sign in).
Esquema de entrada
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"minLength": 8,
"maxLength": 64
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
},
"required": [
"job_id",
"context",
"llm_model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Esquema de salida
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"job_id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"pending",
"completed",
"error"
]
},
"result": {
"type": "object",
"properties": {
"image_url": {
"type": "string"
},
"video_url": {
"type": "string"
},
"edited_image_id": {
"type": "number"
}
},
"additionalProperties": false
},
"error": {
"type": "object",
"properties": {
"message": {
"type": "string"
},
"refunded": {
"type": "boolean"
},
"code": {
"type": "string"
}
},
"required": [
"message",
"refunded"
],
"additionalProperties": false
}
},
"required": [
"job_id",
"status"
],
"additionalProperties": false
},
{
"type": "object",
"properties": {
"code": {
"type": "string"
},
"message": {
"type": "string"
}
},
"required": [
"code",
"message"
],
"additionalProperties": {}
}
]
}Comunidad
Evidencia
Observaciones recientes
verificadoversión no registrada12 herramientas