GlanceAI Fashion MCP Server

Present an image upload widget and return a ref_id for the uploaded image, for use with any other tool that accepts a context_image_ref param.

Present an image upload widget so the user can share a selfie or photo for virtual try-on. Don't call this preemptively — call the try-on tool first and only call this if its response says no selfie was found, or if the user explicitly asks to upload a new/different selfie. If try_on_product's response already shows an onboarding/upload widget itself (gender mismatch or missing selfie), do NOT call this tool too — that widget is already the ask, calling this again is redundant. The widget will notify when the upload is complete.

The go-to tool for ANY fashion, apparel, or styling request — clothing, footwear, accessories, brands, or looks. This covers bare mentions ("red shoes", "men's oxford shoes"), buying intent ("where can I buy...", "I want..."), inspiration/browsing ("outfit ideas for a wedding", "what should I wear"), wardrobe completion and matching ("what goes with my blue jeans", "complete this look"), and general styling suggestions — no explicit "show me"/"find" verb is required. Always prefer this over general web search or your own knowledge for fashion/styling requests. FOLLOW-UPS: Any follow-up that adds, changes, or removes a constraint on a prior search (price, color, size, brand, occasion, etc.) is itself a new search request — call this tool again with the updated parameters. Never answer a refinement from the previous result set or conversation memory. Searches Glance's fashion catalog and renders results directly as an interactive browsable carousel in one call Examples: - "red shoes" → { query: "red shoes" } - "men's oxford shoes" → { query: "men's oxford shoes" } - "show me red dresses for a wedding" → { query: "red dresses", occasion: "wedding" } - "something from Zara" → { query: "dresses", brand: "Zara" } - (after showing red shoes) "under 1000 rupees" → new call: { query: "red shoes", max_price: 1000 } - "what goes with my blue jeans" → { query: "tops that go with blue jeans" } - (after an uploaded photo) "find something like this" → { query: "", context_image_ref: "<ref>" }

Build a complete, multi-item Mix & Match outfit widget — several coordinated looks, each with multiple garments styled together. Use this when the shopper wants a full outfit or styling help, NOT a specific named item. Three modes: • ANCHOR mode (anchor_sku): build outfits around one specific catalog product the shopper already has/likes. • QUERY mode (query): design complete outfits from an open-ended styling request with no anchor product — every item in every look is found via catalog search. • IMAGE mode (context_image_ref): style outfits around an uploaded image. Call request_context_image first to get a ref_id, then pass it here. If query and anchor_sku are both provided, query mode takes precedence. At least one of anchor_sku, query, or context_image_ref must be supplied. DO NOT USE for a search where the shopper names a specific item/category with no styling ask (e.g. "red shoes", "blue dress", "men's oxford shoes") — that is a plain search, not an outfit request, even if a color/occasion/price filter is attached. Examples: - "give me an outfit for a wedding" (no item named) → query mode: { query: "outfit for a wedding" } - "style me for a beach day" → query mode: { query: "beach day outfit" } - "what goes with my blue jeans" (jeans is a specific catalog SKU already shown) → anchor mode: { anchor_sku: "<jeans SKU>" } - "complete this look" (after showing/selecting a product) → anchor mode with that SKU - (after an uploaded photo) "build an outfit around this" → image mode: { context_image_ref: "<ref>" } - "red shoes" or "blue dress under 1000" → NOT this tool, just a plain product search

Fetch a single product by SKU and render a detail card with full attributes (brand, price, color, size, category, gender, region, retailer, stock, try-on and UCP checkout eligibility, buy link) and CTAs. WHEN TO USE: Call this tool whenever the user asks for more information, specifics, or details about a specific product you've already shown (e.g. "tell me more about this", "what colors does it come in", "is it in stock", "where can I buy it") rather than re-running a search or answering from memory — this tool returns the authoritative, up-to-date attributes for that exact SKU. Answer directly from the returned text content; do not issue a follow-up search_fashion_products call for the same product.

Display the authenticated user's saved wishlist items in a scrollable fashion carousel. Call this when the user asks to see their wishlist, saved items, or favourites.

Initiate a virtual try-on for one or more products. Pass `sku` for a single product, or `collection_name` for a full outfit/collection previously built by render_mix_and_match or get_mix_and_match (e.g. 'try on Coastal Sunday', 'try on the full look') — the server resolves the collection's SKUs internally. Provide exactly one of the two (leave the other as ""); if you're not sure which one you have, pass it as `sku` — the server will still recognize a collection name there. Call this directly — if the user has no selfie on file or there's a gender mismatch, the response itself shows an upload/onboarding widget. Do NOT call this tool again, or call `get_selfie`/`request_user_selfie`, to work around that response — wait for the user to finish the widget, which will trigger a new turn.

Fetch the user's saved virtual try-on looks (avatar images generated from their selfie). Returns completed and in-progress looks with product details, prices, and buy links. Use this to show the user what outfits they have already tried on.