com.almirall/mcp

Est-ce que com.almirall/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.almirall/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 11 outils

• compare_content≈ 459 tokens

  Compare two or more named items, product formats, ranges, topics, or alternatives using indexed website content. Use this when the user asks for differences, similarities, pros/cons, or when to choose one option versus another, for example comparing Almax formats or Physiorelax ranges. Returns grouped evidence for each item so the client can build a grounded comparison.

  Paramètres, retour & exemple (6)

  Paramètres

  • items · array · requis
    Names of the items or topics to compare.
  • query · string · optionnel
    Optional comparison context, such as ingredients, benefits, usage, format, contraindications, or when to choose each option.
  • domain · string · optionnel
    Optional domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • topPerItem · integer · optionnel
    Maximum number of search results to keep per item. Defaults to 3.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "compare_content", "arguments": {"items": []}}

  Exemple de retour

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

• find_content_assets≈ 434 tokens

  Extract image/media asset URLs from indexed markdown text. Use only when the user asks for product images, media files, visual assets, screenshots, WordPress uploads, or image evidence. For textual questions about extracted page content, use search_content instead. Returns asset URLs plus the real page URL where each asset appeared.

  Paramètres, retour & exemple (6)

  Paramètres

  • top · integer · optionnel
    Maximum number of chunks to inspect for assets. Defaults to at least 10.
  • url · string · optionnel
    Optional exact crawled page URL filter.
  • query · string · optionnel
    Optional topic, product, filename, or asset context to search before extracting assets. Defaults to image/product-oriented search.
  • domain · string · optionnel
    Optional exact domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "find_content_assets", "arguments": {"top": 1, "url": "texte", "query": "texte", "domain": "texte", "sourceId": "texte", "userLocation": {}}}

  Exemple de retour

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

• find_pages_by_title≈ 393 tokens

  Resolve the most relevant indexed pages by approximate title match before doing a narrower content search. Use this when the user mentions a brand, product family, or page-like concept but not a domain or URL, and you want to identify the right page first without requiring an exact title match.

  Paramètres, retour & exemple (5)

  Paramètres

  • top · integer · optionnel
    Maximum number of candidate pages to return. Defaults to 10.
  • domain · string · optionnel
    Optional domain filter to narrow title matching.
  • sourceId · string · optionnel
    Optional crawler source id to narrow title matching.
  • titleQuery · string · requis
    Brand, product, or page title hint to match approximately against indexed page titles.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "find_pages_by_title", "arguments": {"titleQuery": "texte"}}

  Exemple de retour

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

• find_product_mentions≈ 500 tokens

  Specialized product extraction tool. Use when the user specifically asks what products a crawled brand/site offers, asks for catalog items, variants, product ranges, formulations, product benefits, ingredients by product, or where product claims appear. If the user is asking a general content question rather than enumerating products, use search_content instead. sourceId and domain are optional filters; if you need to discover the right indexed source before narrowing, use list_sources. Returns grouped product mentions with evidence snippets and real page URLs.

  Paramètres, retour & exemple (6)

  Paramètres

  • top · integer · optionnel
    Maximum number of search results to inspect for product mentions. Defaults to at least 8.
  • query · string · requis
    Natural-language query describing the product, brand, category, or benefit to detect.
  • domain · string · optionnel
    Optional domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • productHint · string · optionnel
    Optional known product or brand name to bias extraction and grouping.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

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

  Exemple de retour

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

• get_chunk≈ 366 tokens

  Retrieve one concrete indexed chunk by uid, or by documentId plus chunkIndex. Optionally returns adjacent chunks from the same document for context.

  Paramètres, retour & exemple (6)

  Paramètres

  • uid · string · optionnel
    Exact Azure Search uid for the chunk.
  • chunkIndex · integer · optionnel
    Chunk index inside the document.
  • documentId · string · optionnel
    Document id. Required when looking up by chunkIndex.
  • contextAfter · integer · optionnel
    Number of following chunks to include. Defaults to 0.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.
  • contextBefore · integer · optionnel
    Number of previous chunks to include. Defaults to 0.

  Exemple d'appel

  {"name": "get_chunk", "arguments": {"uid": "texte", "chunkIndex": 1, "documentId": "texte", "contextAfter": 1, "userLocation": {}, "contextBefore": 1}}

  Exemple de retour

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

• get_page≈ 340 tokens

  Reconstruct a page by documentId or url. Returns chunks ordered by chunkIndex plus a compact heading structure.

  Paramètres, retour & exemple (6)

  Paramètres

  • top · integer · optionnel
    Maximum chunks to return. Defaults to 30.
  • url · string · optionnel
    Exact crawled page URL to reconstruct.
  • domain · string · optionnel
    Optional exact domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional source id filter, for example physio-relax-de.
  • documentId · string · optionnel
    Document id to reconstruct.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "get_page", "arguments": {"top": 1, "url": "texte", "domain": "texte", "sourceId": "texte", "documentId": "texte", "userLocation": {}}}

  Exemple de retour

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

• get_source_map≈ 342 tokens

  Build a navigable map of an indexed source or domain with pages, documents, headings, and chunk ranges.

  Paramètres, retour & exemple (6)

  Paramètres

  • top · integer · optionnel
    Maximum chunks to inspect for the map. Defaults to 30.
  • url · string · optionnel
    Optional exact page URL filter.
  • domain · string · optionnel
    Optional exact domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • documentId · string · optionnel
    Optional document id filter.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "get_source_map", "arguments": {"top": 1, "url": "texte", "domain": "texte", "sourceId": "texte", "documentId": "texte", "userLocation": {}}}

  Exemple de retour

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

• list_pages≈ 345 tokens

  List indexed pages available within a sourceId or domain. Use this to discover which page URLs/documents exist before requesting a full page.

  Paramètres, retour & exemple (5)

  Paramètres

  • top · integer · optionnel
    Maximum chunks to inspect for page discovery. Defaults to 30.
  • query · string · optionnel
    Optional search query to narrow page discovery. Use * or omit for broad discovery.
  • domain · string · optionnel
    Optional exact domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "list_pages", "arguments": {"top": 1, "query": "texte", "domain": "texte", "sourceId": "texte", "userLocation": {}}}

  Exemple de retour

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

• list_sources≈ 482 tokens

  Discovery tool for indexed brands, sites, and domains. Use this when you need to discover or disambiguate which indexed domain/sourceId corresponds to a brand or product name, especially if an initial broad search needs narrowing. search_content does not require domain or sourceId, so prefer calling list_sources as an optional discovery step rather than as a mandatory prerequisite. It helps determine whether this MCP has a relevant indexed source and which domain or sourceId to pass into search_content or other tools.

  Paramètres, retour & exemple (6)

  Paramètres

  • top · integer · optionnel
    Maximum chunks to inspect for source discovery. Defaults to 30.
  • skip · integer · optionnel
    Number of matching chunks to skip before collecting the next page of sources. Defaults to 0.
  • query · string · optionnel
    Optional query to list sources related to a topic. Use * or omit for broad source discovery.
  • domain · string · optionnel
    Optional domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "list_sources", "arguments": {"top": 1, "skip": 1, "query": "texte", "domain": "texte", "sourceId": "texte", "userLocation": {}}}

  Exemple de retour

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

• match_almax_prompt≈ 143 tokens

  Classify a Spanish prompt or phrase related to Almax into the closest editorial intent from the corpus. Use this when the client needs to detect which predefined Almax topic a user sentence matches before routing to another tool or template.

  Paramètres, retour & exemple (1)

  Paramètres

  • text · string · requis
    Phrase, prompt, or user text to classify.

  Exemple d'appel

  {"name": "match_almax_prompt", "arguments": {"text": "texte"}}

  Exemple de retour

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

• search_content≈ 744 tokens

  Primary tool for answering natural-language questions over indexed website and landing-page content. Use this whenever the user asks what a brand, product, or site says about ingredients, plant extracts, composition, contraindications, usage, benefits, claims, FAQs, or evidence. This includes questions that only mention a brand or product name, for example 'What ingredients or plant extracts does Physio Relax mention?'. Call this tool directly with the question even if domain or sourceId are unknown; those fields are optional narrowing filters, not required inputs. If you need to discover or disambiguate the indexed domain or sourceId for a second narrowed call, use list_sources. Searches content with keyword, semantic, and vector search, and can filter by domain, url, sourceId, or documentId. If no search results are found, the tool returns only a no-results text message. Use that message as the entire user-facing answer, translating it to the user's language while preserving its meaning. The final answer must explicitly say that no sufficient information or indexed mention was found in Almirall's public content for the query, avoid confirming unsupported details, and suggest another question or Almirall's official channels. When this no-results message is returned, stop and do not add counts, bullet lists, related products, examples, search traces, or conclusions from auxiliary tool calls. Do not summarize, explain, or replace it with an unrelated response.

  Paramètres, retour & exemple (7)

  Paramètres

  • top · integer · optionnel
    Maximum number of search results to return. Defaults to the server setting.
  • url · string · optionnel
    Optional exact crawled page URL filter.
  • query · string · requis
    Natural-language question or keywords to search in crawled website content.
  • domain · string · optionnel
    Optional exact domain filter, for example physio-relax.de.
  • sourceId · string · optionnel
    Optional crawler source id, for example physio-relax-de.
  • documentId · string · optionnel
    Optional crawler document id to restrict results to one indexed page/document.
  • userLocation · object · optionnel
    Optional approximate user location. Include only if the client or user has explicitly made it available; do not infer or guess it.

  Exemple d'appel

  {"name": "search_content", "arguments": {"query": "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://mcp.almirall.com/mcp