Search millions of CC0 public-domain AI images: previews, dimensions, provenance, license.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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).
In one sentence, what is the user trying to make or find?
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.
Tier key from list_models (e.g. 720p, 1080p, 720p-audio)
Video model id from list_models (default: H3 Max)
Required unless start_image is given
Animate from this image (stock id or your edited image id)
Text-to-video only; a start image sets the ratio
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.
Clip length; must be one of the model's durations
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
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).
| Argument | Type | Description |
|---|---|---|
| tier | string | Tier key from list_models (e.g. 720p, 1080p, 720p-audio) |
| model | string | Video model id from list_models (default: H3 Max) |
| prompt | string | Required unless start_image is given |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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. |
| start_image | any | Animate from this image (stock id or your edited image id) |
| aspect_ratio | string | Text-to-video only; a start image sets the ratio |
| conversation_id | string | 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. |
| negative_prompt | string | |
| duration_seconds | integer | Clip length; must be one of the model's durations |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"properties": {
"tier": {
"type": "string",
"maxLength": 24,
"description": "Tier key from list_models (e.g. 720p, 1080p, 720p-audio)"
},
"model": {
"type": "string",
"maxLength": 64,
"description": "Video model id from list_models (default: H3 Max)"
},
"prompt": {
"type": "string",
"maxLength": 2000,
"description": "Required unless start_image is given"
},
"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."
},
"start_image": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"maxLength": 64,
"minLength": 1
}
],
"description": "Animate from this image (stock id or your edited image id)"
},
"aspect_ratio": {
"enum": [
"9:16",
"4:5",
"3:4",
"2:3",
"1:1",
"3:2",
"4:3",
"5:4",
"16:9"
],
"type": "string",
"description": "Text-to-video only; a start image sets the ratio"
},
"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."
},
"negative_prompt": {
"type": "string",
"maxLength": 1000
},
"duration_seconds": {
"type": "integer",
"maximum": 30,
"minimum": 1,
"description": "Clip length; must be one of the model's durations"
}
}
}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).
| Argument | Type | Description |
|---|---|---|
| id* | any | Stock image id or your own edited image id |
| format | string | Default jpg (the original) |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"context",
"llm_model"
],
"properties": {
"id": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"pattern": "^\\d+$"
}
],
"description": "Stock image id or your own edited image id"
},
"format": {
"enum": [
"jpg",
"png"
],
"type": "string",
"description": "Default jpg (the original)"
},
"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."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| id* | integer | Numeric image id from a previous result |
| page | integer | Page number, 1-5 |
| limit | integer | Results to return, 1-12 (default 12). Ask for fewer to save tokens. |
| locale | string | Site locale for the user (default en). Titles and page links are localized; descriptions are English. |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
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).
| Argument | Type | Description |
|---|---|---|
| tier | string | Tier key from list_models (e.g. 1k, 2k, standard). Default: the model's default tier. |
| model | string | Model id from list_models. Default: the site default for subscribers, the free model otherwise. |
| prompt* | string | |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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. |
| aspect_ratio | string | |
| conversation_id | string | 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. |
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).
| Argument | Type | Description |
|---|---|---|
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"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."
}
}
}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. Also shows the signed-in user's own edited images (ids ≥ 10000000000, as returned by generate_image, resize_image and upscale_image).
| Argument | Type | Description |
|---|---|---|
| id* | any | Numeric image id (from search results), one of your own edited image ids (from a generate / resize / upscale result; needs the signed-in account), or the image's CDN uuid |
| locale | string | Site locale for the user (default en). Titles and page links are localized; descriptions are English. |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
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).
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"job_id",
"context",
"llm_model"
],
"properties": {
"job_id": {
"type": "string",
"maxLength": 64,
"minLength": 8
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
}
}License and usage terms for all StockCake images (site-wide CC0 / public domain).
| Argument | Type | Description |
|---|---|---|
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess. |
| conversation_id | string | Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"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."
}
}
}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).
| Argument | Type | Description |
|---|---|---|
| kind | string | Return only one catalog |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"context",
"llm_model"
],
"properties": {
"kind": {
"enum": [
"image",
"video"
],
"type": "string",
"description": "Return only one catalog"
},
"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."
}
}
}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. Output is the model's native size — about 1.5 megapixels, up to 1536 px on the long edge — whatever the source size; the result reports exact dimensions. For print or larger web use, run upscale_image on the result. 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).
| Argument | Type | Description |
|---|---|---|
| image* | any | 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. |
| prompt* | string | What should fill the extended canvas, e.g. 'extend the sandy beach and sky; keep the subject unchanged, do not crop or stretch' |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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. |
| aspect_ratio* | string | Target ratio |
| conversation_id | string | 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. |
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 for this query with counts (how many current matches carry each); both are exact filters, so a small count means few results. Start with a short query; when total_results is small or off-target, retry with fewer keywords or different phrasing.
| Argument | Type | Description |
|---|---|---|
| mood | string | Exact facet value — pick one from refinements.mood of a previous search_images result (check refinements.counts.mood first: it is a hard filter, not a boost) |
| page | integer | Page number, 1-5 |
| type | string | |
| color | string | Dominant color, e.g. a hex value like #ff0000 |
| limit | integer | Results to return, 1-12 (default 12). Ask for fewer to save tokens. |
| query* | string | 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. |
| style | string | Exact facet value — pick one from refinements.style of a previous search_images result (check refinements.counts.style first: it is a hard filter, not a boost) |
Send feedback about this server to its developers. Most important: report a missing capability whenever no available tool fits your task, even if you can work around it (feedback_type "missing_capability"). Also welcome: a tool that failed or confused you, an unhelpful error, or something that worked well. This records the feedback; it does not add or change tools. Do not include user PII or sensitive content.
| Argument | Type | Description |
|---|---|---|
| details | string | Optional longer context: what you tried, exact parameter values, the error text you saw, and any workaround you used. Omit when the summary says it all. |
| summary* | string | One self-contained sentence. For 'missing_capability': the capability you needed, e.g. 'No tool to delete multiple cohorts in one call.' For 'issue': the tool and the problem, e.g. 'query-trends rejects relative date ranges with an unclear error.' |
| llm_model* | string | 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. |
| sentiment | string | Optional: how the experience felt overall. |
| tool_name | string | Optional: the existing tool this feedback is about (for 'issue' or 'praise'). Leave empty for 'missing_capability' - the point is that no tool fits. |
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).
| Argument | Type | Description |
|---|---|---|
| image* | any | 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* | any | |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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 | string | 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. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"image",
"scale",
"context",
"llm_model"
],
"properties": {
"image": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"maxLength": 64,
"minLength": 1
}
],
"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."
}
}
}{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"context",
"llm_model"
],
"properties": {
"id": {
"type": "integer",
"maximum": 9007199254740991,
"description": "Numeric image id from a previous result",
"exclusiveMinimum": 0
},
"page": {
"type": "integer",
"maximum": 5,
"minimum": 1,
"description": "Page number, 1-5"
},
"limit": {
"type": "integer",
"maximum": 12,
"minimum": 1,
"description": "Results to return, 1-12 (default 12). Ask for fewer to save tokens."
},
"locale": {
"enum": [
"en",
"de",
"es",
"fa",
"fr",
"it",
"ja",
"pt"
],
"type": "string",
"description": "Site locale for the user (default en). Titles and page links are localized; descriptions are English."
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
}
}
}| reference_images | array | Stock image ids or your own edited image ids used as references |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"prompt",
"context",
"llm_model"
],
"properties": {
"tier": {
"type": "string",
"maxLength": 16,
"description": "Tier key from list_models (e.g. 1k, 2k, standard). Default: the model's default tier."
},
"model": {
"type": "string",
"maxLength": 64,
"description": "Model id from list_models. Default: the site default for subscribers, the free model otherwise."
},
"prompt": {
"type": "string",
"maxLength": 2000,
"minLength": 1
},
"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."
},
"aspect_ratio": {
"enum": [
"9:16",
"4:5",
"3:4",
"2:3",
"1:1",
"3:2",
"4:3",
"5:4",
"16:9"
],
"type": "string"
},
"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."
},
"reference_images": {
"type": "array",
"items": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"maxLength": 64,
"minLength": 1
}
],
"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."
},
"maxItems": 9,
"description": "Stock image ids or your own edited image ids used as references"
}
}
}| include_preview | boolean | Default true. Set false to skip the inline preview image and save tokens. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"context",
"llm_model"
],
"properties": {
"id": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"maxLength": 64,
"minLength": 4
}
],
"description": "Numeric image id (from search results), one of your own edited image ids (from a generate / resize / upscale result; needs the signed-in account), or the image's CDN uuid"
},
"locale": {
"enum": [
"en",
"de",
"es",
"fa",
"fr",
"it",
"ja",
"pt"
],
"type": "string",
"description": "Site locale for the user (default en). Titles and page links are localized; descriptions are English."
},
"context": {
"type": "string",
"description": "In one sentence, what is the user trying to make or find?"
},
"llm_model": {
"type": "string",
"description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."
},
"conversation_id": {
"type": "string",
"description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."
},
"include_preview": {
"type": "boolean",
"description": "Default true. Set false to skip the inline preview image and save tokens."
}
}
}{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"image",
"aspect_ratio",
"prompt",
"context",
"llm_model"
],
"properties": {
"image": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"exclusiveMinimum": 0
},
{
"type": "string",
"maxLength": 64,
"minLength": 1
}
],
"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."
},
"prompt": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"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."
},
"aspect_ratio": {
"enum": [
"9:16",
"4:5",
"3:4",
"2:3",
"1:1",
"3:2",
"4:3",
"5:4",
"16:9"
],
"type": "string",
"description": "Target ratio"
},
"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."
}
}
}| locale | string | Site locale for the user (default en). Titles and page links are localized; descriptions are English. |
| context* | string | In one sentence, what is the user trying to make or find? |
| llm_model* | string | 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. |
| orientation | string |
| conversation_id | string | 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. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"query",
"context",
"llm_model"
],
"properties": {
"mood": {
"type": "string",
"maxLength": 50,
"description": "Exact facet value — pick one from refinements.mood of a previous search_images result (check refinements.counts.mood first: it is a hard filter, not a boost)"
},
"page": {
"type": "integer",
"maximum": 5,
"minimum": 1,
"description": "Page number, 1-5"
},
"type": {
"enum": [
"photos",
"illustrations",
"digital-art",
"3d"
],
"type": "string"
},
"color": {
"type": "string",
"maxLength": 30,
"description": "Dominant color, e.g. a hex value like #ff0000"
},
"limit": {
"type": "integer",
"maximum": 12,
"minimum": 1,
"description": "Results to return, 1-12 (default 12). Ask for fewer to save tokens."
},
"query": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"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."
},
"style": {
"type": "string",
"maxLength": 50,
"description": "Exact facet value — pick one from refinements.style of a previous search_images result (check refinements.counts.style first: it is a hard filter, not a boost)"
},
"locale": {
"enum": [
"en",
"de",
"es",
"fa",
"fr",
"it",
"ja",
"pt"
],
"type": "string",
"description": "Site locale for the user (default en). Titles and page links are localized; descriptions are English."
},
"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."
},
"orientation": {
"enum": [
"landscape",
"portrait",
"square"
],
"type": "string"
},
"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."
}
}
}| feedback_type* | string | What kind of feedback this is. Use 'missing_capability' when the tool you needed does not exist in the tool list - nothing failed, the capability is absent (this is the most valuable report; send it even if you found a workaround). Use 'issue' when an existing tool behaved badly: it failed, returned a confusing error, or its description or schema misled you. Use 'praise' when something worked notably well. Use 'other' for anything else. |
| task_completed | boolean | Optional: whether you still completed the user's task despite the problem. |
| conversation_id | string | 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. |
| friction_points | string | Optional: the specific moments that slowed you down, as short bullet-like sentences, quoting exact tool names, parameters, or error text. |
| suggested_improvement | string | Optional: the concrete change that would have helped, e.g. the tool to add, the description to reword, or the error message to improve. |
{
"type": "object",
"required": [
"feedback_type",
"summary",
"llm_model"
],
"properties": {
"details": {
"type": "string",
"description": "Optional longer context: what you tried, exact parameter values, the error text you saw, and any workaround you used. Omit when the summary says it all."
},
"summary": {
"type": "string",
"description": "One self-contained sentence. For 'missing_capability': the capability you needed, e.g. 'No tool to delete multiple cohorts in one call.' For 'issue': the tool and the problem, e.g. 'query-trends rejects relative date ranges with an unclear error.'"
},
"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."
},
"sentiment": {
"enum": [
"positive",
"neutral",
"negative",
"mixed"
],
"type": "string",
"description": "Optional: how the experience felt overall."
},
"tool_name": {
"type": "string",
"description": "Optional: the existing tool this feedback is about (for 'issue' or 'praise'). Leave empty for 'missing_capability' - the point is that no tool fits."
},
"feedback_type": {
"enum": [
"missing_capability",
"issue",
"praise",
"other"
],
"type": "string",
"description": "What kind of feedback this is. Use 'missing_capability' when the tool you needed does not exist in the tool list - nothing failed, the capability is absent (this is the most valuable report; send it even if you found a workaround). Use 'issue' when an existing tool behaved badly: it failed, returned a confusing error, or its description or schema misled you. Use 'praise' when something worked notably well. Use 'other' for anything else."
},
"task_completed": {
"type": "boolean",
"description": "Optional: whether you still completed the user's task despite the problem."
},
"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."
},
"friction_points": {
"type": "string",
"description": "Optional: the specific moments that slowed you down, as short bullet-like sentences, quoting exact tool names, parameters, or error text."
},
"suggested_improvement": {
"type": "string",
"description": "Optional: the concrete change that would have helped, e.g. the tool to add, the description to reword, or the error message to improve."
}
}
}