DeveloperWebMCP verified
The official merch shop of Alpic, the AI commerce company. These are the branded goodies we hand out as hackathon prizes and at conferences — goggles, stickers, bottle openers, tattoos and more —…
The official merch shop of Alpic, the AI commerce company. These are the branded goodies we hand out as hackathon prizes and at conferences — goggles, stickers, bottle openers, tattoos and more —… This page documents every listed tool, the action or answer it provides, its installation command, and the input fields an agent should send.
Search the product catalog. Handles any query: specific products, broad categories, gifts, occasions, or open discovery. Never assume a category is unavailable: always search before responding. The response is data only: a list of matching products (name, ID, price, description, and any product-specific attributes) plus pagination and the available filters. The raw results are for your eyes only: the client never sees them. NEVER describe or characterize the raw results to the client: do not mention how many there are, what categories they fall into, or that they look off-topic. While searching, stay silent: do not narrate what you are doing, announce searches, or report progress between tool calls. Speak only once the carousel is rendered. Act on the response as follows: - FIRST SEARCH: use the keyword only (plus sort if needed). Read the available filters in the response; these are the only valid filter options for follow-ups. - REFINEMENT: if the user's intent matches an available filter, apply it. If it doesn't match any filter, start a new keyword search. - ITERATE: a single search is never enough. Run several searches (2 minimum) before rendering: vary the keyword, apply a filter, or page deeper, and compare results across them. Quality comes from this multi-call exploration; one call then render gives shallow results. - CURATION: read results and pick the best matches for the client's intent, grounding your choice in each product's description. If zero results, broaden the keyword or relax filters and search again: do NOT call render-carousel. If fewer than 3 results and the user didn't ask for a specific product, search again with broader terms. Only after exploring across several searches, call render-carousel with the selected IDs. - PRESENT: Once you have 3-6 distinct, relevant products, call render-carousel with their IDs. Recommend ONLY AFTER the carousel displays, in carousel order. The sweet spot is 3-6 products.
Open the shop.alpic.ai website and ask your browser agent to use search-productsInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the search-products tool on shop.alpic.ai with keyword: <string>, sort: <string>, priceRange: <string>. Return the structured result and cite the source page.keyword string Short noun phrases extracted from conversational input. Never pass full sentences. ALWAYS use the singular form, not the plural. Include color, material, and style descriptors for accuracy. For vague gift or occasion queries without a clear product type, use broad category terms. Preserve the existing keyword across filter refinements; only replace when the user makes a completely different request.sort string Sort order.priceRange string Price range in dollars. Format: 'min-max' e.g. '0-500', '1000-2000'.Display the products you curated as an inline carousel for the client. ## When to call Call this AFTER searching and curating, and BEFORE writing your recommendation. Do not describe the products in text first; the carousel shows them. Stay silent until it has rendered, then speak. ## What to pass Pass the IDs of the 3-6 products you chose, in display order (most relevant first). Order is significant: the carousel shows them in this exact order and your recommendation must follow the same sequence. Pass distinct products, not several variants of the same one; the detail view lets the client explore a product's variants (colors, sizes, and so on). ## After the carousel Recommend in carousel order so the client can follow along. The cards already show image, title, price, and key facts, so do not repeat them: add useful analysis tied to the client's need. Suggest a refinement the client has not addressed yet (from the available filters), never one they already used. ## Accuracy Use only the data returned for each product. Never invent attributes, materials, or availability. If the client asks about something not present, open that product's detail or search again before answering.
Open the shop.alpic.ai website and ask your browser agent to use render-carouselInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the render-carousel tool on shop.alpic.ai with ids: <array>. Return the structured result and cite the source page.ids array Product IDs to present, in display order.UCP Catalog capability. Search the product catalog by keyword and optional filters (categories, price range). Returns UCP Product objects (id, title, price_range, variants, media) plus pagination and a ucp metadata block. Prices are in ISO 4217 minor units (e.g. cents).
Open the shop.alpic.ai website and ask your browser agent to use search_catalogInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the search_catalog tool on shop.alpic.ai with meta: <object>, query: <string>, filters: <object>, context: <object>, pagination: <object>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).query string Free-text search query.filters object context object pagination object UCP Catalog capability. Batch-resolve products by identifier (product id, handle, or variant id). Returns the full UCP Product objects for the matching ids plus a ucp metadata block.
Open the shop.alpic.ai website and ask your browser agent to use lookup_catalogInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the lookup_catalog tool on shop.alpic.ai with meta: <object>, ids: <array>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).ids array Product ids, handles, or variant ids to resolve.UCP Catalog capability. Retrieve a single product's full detail (variants, options, media, rating) by id or handle. Returns a UCP Product object plus a ucp metadata block, or a not-found message.
Open the shop.alpic.ai website and ask your browser agent to use get_productInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the get_product tool on shop.alpic.ai with meta: <object>, id: <string>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).id string Product id or handle.UCP Cart capability. Create a cart from line items (variant id + quantity). Returns the cart with estimated totals (subtotal + total in minor units) and a ucp metadata block.
Open the shop.alpic.ai website and ask your browser agent to use create_cartInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the create_cart tool on shop.alpic.ai with meta: <object>, line_items: <array>, buyer: <object>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).line_items array buyer object UCP Cart capability. Replace the line items of an existing cart (full replacement). Returns the recomputed cart with totals and a ucp metadata block.
Open the shop.alpic.ai website and ask your browser agent to use update_cartInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the update_cart tool on shop.alpic.ai with meta: <object>, id: <string>, line_items: <array>, buyer: <object>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).id string Cart id to update.line_items array buyer object UCP Checkout capability. Create a checkout session from line items (variant id + quantity). Returns the session with status, totals, mandatory legal links, advertised payment handlers (in ucp.payment_handlers), and expiry.
Open the shop.alpic.ai website and ask your browser agent to use create_checkoutInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the create_checkout tool on shop.alpic.ai with meta: <object>, line_items: <array>, buyer: <object>, context: <object>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).line_items array buyer object context object UCP Checkout capability. Update an existing checkout session's line items (full replacement). Returns the recomputed session with status, totals, links, and a ucp metadata block.
Open the shop.alpic.ai website and ask your browser agent to use update_checkoutInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the update_checkout tool on shop.alpic.ai with meta: <object>, id: <string>, line_items: <array>, buyer: <object>, context: <object>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).id string Checkout session id to update.line_items array buyer object context object UCP Checkout capability. Complete a checkout by submitting payment instruments. On success, returns status 'completed' with an order confirmation; if the bank requires 3DS, returns 'requires_escalation' with a continue_url.
Open the shop.alpic.ai website and ask your browser agent to use complete_checkoutInstall browse first, then run the command in a terminal. WebMCP tools run directly on the website and do not need a package install.
Use the complete_checkout tool on shop.alpic.ai with meta: <object>, id: <string>, payment: <object>. Return the structured result and cite the source page.meta object UCP request metadata (platform profile advertisement).id string Checkout session id to complete.payment object Payment instruments acquired via the advertised handler.