ai.memestack/mcp

Est-ce que ai.memestack/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.memestack/mcp » 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 21 outils

• browse_by_category≈ 3002 tokens

  Get a category and its featured images. Categories group related tags (e.g. "charts", "memes", "lightning-network").

  Paramètres, retour & exemple (1)

  Paramètres

  • category · string · requis
    Category slug (e.g. "charts", "memes")

  Exemple d'appel

  {"name": "browse_by_category", "arguments": {"category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "slug": "texte", "description": "texte", "featured_images": [], "citations_combined": {}}}

• browse_by_tag≈ 3159 tokens

  Browse images for a specific tag. Returns the tag profile (description, stats) and optionally a paginated list of images tagged with it. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (4)

  Paramètres

  • tag · string · requis
    Tag slug (e.g. "bitcoin", "meme", "lightning")
  • limit · number · optionnel
    Images per page (1-50, default 10). When provided, images are included in the response.
  • offset · number · optionnel
    Pagination offset (default 0)
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "browse_by_tag", "arguments": {"tag": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "slug": "texte", "total": 1, "images": [], "description": "texte", "image_count": 1, "related_tags": [], "citations_combined": {}}}

• browse_images≈ 3061 tokens

  Browse and filter the image gallery without a search query. Useful for discovering content by tag, trending, or recent uploads. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (5)

  Paramètres

  • tag · string · optionnel
    Filter by tag slug (e.g. "bitcoin", "meme")
  • sort · string · optionnel · newest | popular | oldest | trending
    Sort order (default: newest)
  • limit · number · optionnel
    Results per page (1-50, default 10)
  • offset · number · optionnel
    Pagination offset (default 0)
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "browse_images", "arguments": {"tag": "texte", "sort": "newest", "limit": 1, "offset": 1, "include_controversial": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "images": [], "citations_combined": {}}}

• cite_image≈ 1286 tokens

  Generate canonical attribution blocks for one or more MemeStack images. Returns markdown, HTML, and plain-text citation strings ready to paste into your output, plus a combined block for citing multiple images at once.

  Paramètres, retour & exemple (1)

  Paramètres

  • image_ids · array · requis
    Up to 50 image UUIDs

  Exemple d'appel

  {"name": "cite_image", "arguments": {"image_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"combined": {}, "citations": [], "missing_ids": []}}

• find_meme_for_text≈ 3382 tokens

  Find memes that capture a vibe, idea, or concept, ready to embed with citation blocks. Use this when writing posts, articles, or social content and you need a meme to illustrate a point. Returns only images tagged as memes (the gallery's Memes filter), so it may come back empty when no meme fits. To search every kind of image, use search_images. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (3)

  Paramètres

  • vibe · string · requis
    The core idea in one to three words, e.g. "procrastination", "burnout" or "imposter syndrome". Every extra word narrows the match: a long descriptive phrase finds only weaker "closest" results, so leave out synonyms and words like "funny" or "relatable".
  • limit · number · optionnel
    How many memes to return (1-20, default 5)
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "find_meme_for_text", "arguments": {"vibe": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "images": [], "has_more": true, "match_quality": "strong", "query_language": "texte", "translated_query": "texte", "citations_combined": {}}}

• find_related≈ 3059 tokens

  Find semantically related images using AI embedding similarity. Returns images with similar meaning/topic. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    Source image UUID
  • limit · number · optionnel
    Max results (1-20, default 10)
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "find_related", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "images": [], "citations_combined": {}}}

• find_similar≈ 3055 tokens

  Find visually similar images using perceptual hash matching. Returns images that look alike. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    Source image UUID
  • limit · number · optionnel
    Max results (1-20, default 10)
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "find_similar", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "images": [], "citations_combined": {}}}

• generate_meme≈ 555 tokens

  Generate a new image from a text prompt using AI (Grok Imagine). Paid tool - billed per call via the agent payment rails (x402/L402); not covered by any free quota. Generation runs asynchronously on the server and this call polls until it completes, up to ~90 seconds. If you get a "still running" error, call the tool again with the SAME payment proof to resume polling - you will never be charged twice for one payment. Price: $0.08 standard or $0.20 quality, paid in sats over Lightning at the current BTC/USD rate or in USDC on Base. Note for x402 clients: "quality" mode exceeds the agents-SDK default per-call cap of $0.10 - raise maxPaymentValue in withX402Client to use it.

  Paramètres, retour & exemple (3)

  Paramètres

  • mode · string · optionnel · standard | quality
    Generation quality tier - "standard" (default, cheaper) or "quality" (higher fidelity, costs more).
  • prompt · string · requis
    Text description of the image to generate (max 2000 characters).
  • aspect_ratio · string · optionnel · 1:1 | 3:4 | 16:9
    Output image aspect ratio (default "1:1").

  Exemple d'appel

  {"name": "generate_meme", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "tags": [], "caption": "texte", "image_id": "texte", "image_url": "texte", "thumbnail_url": "texte"}}

• get_image≈ 2930 tokens

  Get full metadata for a specific image by ID, including caption, alt text, tags, OCR text, zap stats, and URLs. For a chart that is part of a series, chart.series lists every edition (other years) by id.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Image UUID

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "size": 1, "tags": [], "chart": {}, "match": "strong", "width": 1, "height": 1, "rights": {}, "caption": "texte", "alt_text": "texte", "citation": {}, "page_url": "texte"}}

• get_leaderboard≈ 3134 tokens

  Get top-ranked images by zaps received, or top zappers by amount zapped, over a time period.

  Paramètres, retour & exemple (2)

  Paramètres

  • type · string · requis · images | zappers
    Leaderboard type
  • period · string · optionnel · day | week | month | all
    Time period (default: week)

  Exemple d'appel

  {"name": "get_leaderboard", "arguments": {"type": "images"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"users": [], "images": [], "period": "texte", "citations_combined": {}}}

• get_meme_variants≈ 5787 tokens

  Get every variant of a meme tracked on MemeStack, given the ID of any one of them. Returns the dominant (most popular) version plus each variant, with citation blocks for each. Use this to research how a meme has evolved or to find variants of a known image.

  Paramètres, retour & exemple (1)

  Paramètres

  • image_id · string · requis
    Image UUID

  Exemple d'appel

  {"name": "get_meme_variants", "arguments": {"image_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"dominant": {}, "variants": [], "total_variants": 1, "citations_combined": {}}}

• get_tag_profile≈ 264 tokens

  Get the profile for a tag (description, image count, total zaps, related tags) without fetching any images. Use browse_by_tag to also retrieve images.

  Paramètres, retour & exemple (1)

  Paramètres

  • tag · string · requis
    Tag slug (e.g. "bitcoin", "meme")

  Exemple d'appel

  {"name": "get_tag_profile", "arguments": {"tag": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "slug": "texte", "description": "texte", "image_count": 1, "related_tags": []}}

• get_user_profile≈ 246 tokens

  Get a user's public profile including display name, stats, and avatar info.

  Paramètres, retour & exemple (1)

  Paramètres

  • identifier · string · requis
    User public key (hex) or UUID

  Exemple d'appel

  {"name": "get_user_profile", "arguments": {"identifier": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "created_at": "texte", "has_avatar": true, "display_name": "texte", "approved_image_count": 1}}

• list_categories≈ 241 tokens

  List all available image categories. Use this to discover what categories exist before calling browse_by_category.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_categories", "arguments": {}}

  Exemple de retour

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

• popular_tags≈ 259 tokens

  List the most-used tags on MemeStack by all-time usage count. (Time-period filtering is not yet supported - tag usage is currently counted across the full lifetime of each tag.)

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · number · optionnel
    How many tags to return (1-100, default 20)

  Exemple d'appel

  {"name": "popular_tags", "arguments": {"limit": 1}}

  Exemple de retour

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

• reverse_image_search≈ 3219 tokens

  Find MemeStack images that look visually similar to a given image. Accepts an HTTPS image URL or a `data:image/...;base64,...` URL for bytes pasted into agent context. Returns visually-similar matches via perceptual-hash (dHash) hamming distance, with citation blocks. Heavily rate-limited (10/min/IP) since each call hashes the input. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    HTTPS image URL, or data:image/(jpeg|png|webp);base64,... URL
  • limit · number · optionnel
    Max results (1-20, default 10)
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "reverse_image_search", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"similar": [], "input_meta": {}, "citations_combined": {}}}

• search_charts≈ 3882 tokens

  Search charts, maps and infographics that carry stored metadata of two kinds. Charts from Our World in Data and three statistical publishers (provenance 'authoritative') carry the publishing dataset and its citation, the unit, the regions plotted, the period the chart actually displays (never the dataset's wider history), and whether the source has published newer data since the image was captured. Community-uploaded charts (provenance 'extracted') carry a title, source line, unit and period that were read from the image itself and not checked against the original data. browse_by_tag, browse_by_category, get_leaderboard and get_meme_variants return images WITHOUT this metadata; the other search and image tools include it whenever a row exists. This tool covers only images that HAVE stored metadata, so use search_images for the widest chart coverage. Set publisher_only to keep only the publishers' own charts (licence-clean, citable). Every image carries rights (source publisher/creator/community, licence, attribution line, commercial_use yes/no/unknown - unknown is never a guess), and match_quality says whether the search found any strong match (strong / closest_only / none). Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (9)

  Paramètres

  • limit · number · optionnel
    Results per page (1-50, default 10)
  • query · string · requis
    What the chart should show, in plain words - e.g. "global cereal yields" or "life expectancy by country".
  • offset · number · optionnel
    Pagination offset (default 0)
  • region · string · optionnel
    Restrict to charts that plot this entity exactly as the chart names it, e.g. "World", "Germany".
  • data_to · number · optionnel
    Latest year of interest. See data_from.
  • data_from · number · optionnel
    Earliest year of interest. Matches charts whose DISPLAYED period overlaps [data_from, data_to]. Charts with no provable displayed period are excluded, and the underlying dataset's wider history is never used for this test.
  • chart_source · string · optionnel
    Restrict to one upstream source key: "owid" (Our World in Data), "usda_ers" (USDA Economic Research Service), "eurostat" or "eea" (European Environment Agency), or "extracted" (community charts whose details were read from the image).
  • publisher_only · boolean · optionnel
    Only charts imported from a licence-clean publisher: Our World in Data (CC BY 4.0), the USDA Economic Research Service (US public domain), Eurostat or the European Environment Agency (both CC BY 4.0). Community uploads, including copies of publisher charts, are left out. Default false.
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "search_charts", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "total": 1, "images": [], "has_more": true, "match_quality": "strong", "query_language": "texte", "translated_query": "texte", "citations_combined": {}}}

• search_images≈ 3614 tokens

  Search the MemeStack image gallery. Runs semantic AI and keyword matching in parallel and merges results. Returns images with captions, tags, zap stats, and URLs. Every image carries rights (source publisher/creator/community, licence, attribution line, commercial_use yes/no/unknown - unknown is never a guess), and match_quality says whether the search found any strong match (strong / closest_only / none). Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (9)

  Paramètres

  • q · string · optionnel
    Alias for `query`. Provided so REST-API muscle memory (?q=...) works on the MCP tool too. If both are set, `query` wins.
  • tag · string · optionnel
    Filter results by a single tag slug (backward compat)
  • sort · string · optionnel · newest | popular | oldest
    Sort order (default: relevance)
  • tags · string · optionnel
    Filter results by multiple tag slugs (comma-separated, AND logic - e.g. "bitcoin,meme")
  • limit · number · optionnel
    Results per page (1-50, default 10)
  • query · string · requis
    Search query - combines semantic AI and keyword matching automatically. Use the key words only (e.g. "bitcoin halving infographic"): a long descriptive phrase matches fewer images strongly. Alias: `q` (matches the REST API param name).
  • offset · number · optionnel
    Pagination offset (default 0)
  • publisher_only · boolean · optionnel
    Only charts imported from a licence-clean publisher: Our World in Data (CC BY 4.0), the USDA Economic Research Service (US public domain), Eurostat or the European Environment Agency (both CC BY 4.0). Community uploads, including copies of publisher charts, are left out. Default false.
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

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

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "total": 1, "images": [], "has_more": true, "match_quality": "strong", "query_language": "texte", "translated_query": "texte", "citations_combined": {}}}

• search_text_in_image≈ 3231 tokens

  Search for images by the text written or printed in them (OCR). Different from regular search - only matches the text_in_image field, not captions or tags. Use this to find screenshots of specific quotes, signs, watermarks, or memes with specific embedded text. Results exclude images classified controversial unless include_controversial is true.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · number · optionnel
    Results per page (1-50, default 10)
  • query · string · requis
    Text to search for in image OCR
  • offset · number · optionnel
    Pagination offset
  • include_controversial · boolean · optionnel
    Include images classified controversial (excluded by default).

  Exemple d'appel

  {"name": "search_text_in_image", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "total": 1, "images": [], "has_more": true, "match_quality": "strong", "citations_combined": {}}}

• submit_image≈ 561 tokens

  Submit an image to the MemeStack review queue. Paid tool - $0.10 per submission, paid in sats over Lightning at the current BTC/USD rate or in USDC on Base via the agent payment rails (x402/L402); no account or API key. IMPORTANT: there is NO refund if moderation rejects the submission (duplicate, nsfw/spam, low quality) - the fee is the anti-spam mechanism. Accepted images await human review before publication. Accepts an HTTPS image URL or a data:image/...;base64 URL (JPEG/PNG/WebP, max 8MB). Optional caption/tags/attribution are hints shown to the AI tagger and moderators - never published verbatim. If the call fails or times out, retry with the SAME payment proof to resume - one payment delivers at most one submission and is never charged twice (up to 10 delivery attempts per payment; a corrected image_url is allowed while no submission has been created yet).

  Paramètres, retour & exemple (4)

  Paramètres

  • tags · array · optionnel
    Optional tag hints (max 10).
  • caption · string · optionnel
    Optional caption hint for the AI tagger (admin-visible, never published verbatim).
  • image_url · string · requis
    HTTPS image URL, or data:image/(jpeg|png|webp);base64,... URL. Max 8MB.
  • attribution · string · optionnel
    Optional credit line for the original creator/source (shown to moderators, not published).

  Exemple d'appel

  {"name": "submit_image", "arguments": {"image_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "image_id": "texte", "page_url": "texte"}}

• tag_autocomplete≈ 296 tokens

  Suggest tag slugs matching a prefix. Use this to verify a tag exists before filtering by it, or to discover related tags. Prefix must be >= 2 characters.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · number · optionnel
    Max suggestions (1-50, default 10)
  • prefix · string · requis
    Tag prefix to autocomplete (>= 2 characters), e.g. "bit" -> "bitcoin".

  Exemple d'appel

  {"name": "tag_autocomplete", "arguments": {"prefix": "texte"}}

  Exemple de retour

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

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://mcp.memestack.ai/mcp