Almirall MCP

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.

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

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

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

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

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.

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.

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.

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.

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.

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.