com.stockcake/stockcake

Est-ce que com.stockcake/stockcake est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.stockcake/stockcake » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 13 outils

• create_video≈ 862 tokens

  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).

  Paramètres, retour & exemple (10)

  Paramètres

  • tier · string · optionnel
    Tier key from list_models (e.g. 720p, 1080p, 720p-audio)
  • model · string · optionnel
    Video model id from list_models (default: MiniMax H3)
  • prompt · string · optionnel
    Required unless start_image is given
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · ? · optionnel
    Animate from this image (stock id or your edited image id)
  • aspect_ratio · string · optionnel · 9:16 | 4:5 | 3:4 | 2:3 | 1:1 | 3:2 | 4:3 | 5:4
    Text-to-video only; a start image sets the ratio
  • conversation_id · string · optionnel
    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 · optionnel
  • duration_seconds · integer · optionnel
    Clip length; must be one of the model's durations

  Exemple d'appel

  {"name": "create_video", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• download_image≈ 746 tokens

  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).

  Paramètres, retour & exemple (5)

  Paramètres

  • id · ? · requis
    Stock image id or your own edited image id
  • format · string · optionnel · jpg | png
    Default jpg (the original)
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "download_image", "arguments": {"id": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_similar_images≈ 1011 tokens

  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.

  Paramètres, retour & exemple (7)

  Paramètres

  • id · integer · requis
    Numeric image id from a previous result
  • page · integer · optionnel
    Page number, 1-5
  • limit · integer · optionnel
    Results to return, 1-12 (default 12). Ask for fewer to save tokens.
  • locale · string · optionnel · en | de | es | fa | fr | it | ja | pt
    Site locale for the user (default en). Titles and page links are localized; descriptions are English.
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "find_similar_images", "arguments": {"id": 1, "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"page": 1, "results": [], "has_more": true, "refinements": {}, "total_pages": 1, "license_note": "texte", "total_results": 1}}

• generate_image≈ 960 tokens

  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).

  Paramètres, retour & exemple (8)

  Paramètres

  • tier · string · optionnel
    Tier key from list_models (e.g. 1k, 2k, standard). Default: the model's default tier.
  • model · string · optionnel
    Model id from list_models. Default: the site default for subscribers, the free model otherwise.
  • prompt · string · requis
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel · 9:16 | 4:5 | 3:4 | 2:3 | 1:1 | 3:2 | 4:3 | 5:4
  • conversation_id · string · optionnel
    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 · optionnel
    Stock image ids or your own edited image ids used as references

  Exemple d'appel

  {"name": "generate_image", "arguments": {"prompt": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_account≈ 644 tokens

  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).

  Paramètres, retour & exemple (3)

  Paramètres

  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "get_account", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_image≈ 1059 tokens

  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).

  Paramètres, retour & exemple (6)

  Paramètres

  • id · ? · requis
    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 · optionnel · en | de | es | fa | fr | it | ja | pt
    Site locale for the user (default en). Titles and page links are localized; descriptions are English.
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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 · boolean · optionnel
    Default true. Set false to skip the inline preview image and save tokens.

  Exemple d'appel

  {"name": "get_image", "arguments": {"id": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": 1, "tags": [], "title": "texte", "license": {}, "page_url": "texte", "dimensions": "texte", "provenance": {}, "attribution": {}, "description": "texte", "preview_url": "texte"}}

• get_job≈ 591 tokens

  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).

  Paramètres, retour & exemple (4)

  Paramètres

  • job_id · string · requis
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "get_job", "arguments": {"job_id": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_license_info≈ 332 tokens

  License and usage terms for all StockCake images (site-wide CC0 / public domain).

  Paramètres, retour & exemple (3)

  Paramètres

  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "get_license_info", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_models≈ 923 tokens

  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).

  Paramètres, retour & exemple (4)

  Paramètres

  • kind · string · optionnel · image | video
    Return only one catalog
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "list_models", "arguments": {"context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• resize_image≈ 940 tokens

  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).

  Paramètres, retour & exemple (6)

  Paramètres

  • image · ? · requis
    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 · requis
    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 · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · requis · 9:16 | 4:5 | 3:4 | 2:3 | 1:1 | 3:2 | 4:3 | 5:4
    Target ratio
  • conversation_id · string · optionnel
    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.

  Exemple d'appel

  {"name": "resize_image", "arguments": {"image": "texte", "prompt": "texte", "context": "texte", "llm_model": "texte", "aspect_ratio": "9:16"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_images≈ 1277 tokens

  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.

  Paramètres, retour & exemple (12)

  Paramètres

  • mood · string · optionnel
    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 · optionnel
    Page number, 1-5
  • type · string · optionnel · photos | illustrations | digital-art | 3d
  • color · string · optionnel
    Dominant color, e.g. a hex value like #ff0000
  • limit · integer · optionnel
    Results to return, 1-12 (default 12). Ask for fewer to save tokens.
  • query · string · requis
    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 · optionnel
    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 · string · optionnel · en | de | es | fa | fr | it | ja | pt
    Site locale for the user (default en). Titles and page links are localized; descriptions are English.
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel · landscape | portrait | square
  • conversation_id · string · optionnel
    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.

  Exemple d'appel

  {"name": "search_images", "arguments": {"query": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"page": 1, "results": [], "has_more": true, "refinements": {}, "total_pages": 1, "license_note": "texte", "total_results": 1}}

• send_feedback≈ 846 tokens

  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.

  Paramètres, retour & exemple (10)

  Paramètres

  • details · string · optionnel
    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 · requis
    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 · requis
    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 · optionnel · positive | neutral | negative | mixed
    Optional: how the experience felt overall.
  • tool_name · string · optionnel
    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 · string · requis · missing_capability | issue | praise | other
    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 · optionnel
    Optional: whether you still completed the user's task despite the problem.
  • conversation_id · string · optionnel
    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 · optionnel
    Optional: the specific moments that slowed you down, as short bullet-like sentences, quoting exact tool names, parameters, or error text.
  • suggested_improvement · string · optionnel
    Optional: the concrete change that would have helped, e.g. the tool to add, the description to reword, or the error message to improve.

  Exemple d'appel

  {"name": "send_feedback", "arguments": {"summary": "texte", "llm_model": "texte", "feedback_type": "missing_capability"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• upscale_image≈ 818 tokens

  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).

  Paramètres, retour & exemple (5)

  Paramètres

  • image · ? · requis
    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 · ? · requis
  • context · string · requis
    In one sentence, what is the user trying to make or find?
  • llm_model · string · requis
    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 · optionnel
    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.

  Exemple d'appel

  {"name": "upscale_image", "arguments": {"image": "texte", "scale": "texte", "context": "texte", "llm_model": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://stockcake.com/api/mcp