AI shopping advisor: finds and compares products with merchant prices from daily feed imports.
Scored across 6 tools
Each tool maps to a distinct action in the shopping flow (search → compare → alternatives → recommend → offers → detail), and descriptions explicitly cross-reference each other (e.g. 'search_products already carries the cheapest one'). The only residual overlap is search_products versus recommend_product, since search also claims 'the best product of a kind', but the ranking-vs-listing distinction is stated clearly enough to guide selection.
Every name is a clean snake_case verb_noun pair (compare_products, find_alternatives, get_offers, get_product_text, recommend_product, search_products). The verbs (search/find/compare/recommend/get) accurately signal the operation, so the pattern is fully predictable.
Six tools is well-scoped for a product discovery and price-comparison assistant, with no filler: each tool covers a discrete step in the research workflow. Nothing feels redundant or missing at the structural level.
The surface covers the full research lifecycle: discover, expand, compare, rank, enumerate offers, and describe. Minor gaps exist — get_product_text only works off prior results (no direct lookup by product id), and there is no category/browse, price-history, or cart/checkout tool — but these are workarounds rather than blockers for a recommendation-focused server.
Compare two to five products side by side: brand, category, price range across merchants, merchant count, and the lowest current offer for each. Use when the user is choosing between named products.
Inputs: pids (required), market (required). Returns: note, market, products, empty_reason
Find comparable products to a given product in the same market, optionally within a budget or with specific attribute changes. Use when the user asks for alternatives, cheaper equivalents, or "something like X but Y".
Inputs: pid (required), market (required), limit, direction, +2 more. Returns: note, items, market, direction, +2 more
Return the full list of current merchant offers for one product in a market: merchant, price, currency, stock status, source timestamp, match tier, and a purchase link, cheapest first. Use when the user wants to see every merchant for one product — search_products already carries the cheapest one.
Inputs: pid (required), market (required), limit, include_description. Returns: pid, name, note, brand, +6 more
Edwin's short summary and key features for products from an earlier Edwin result (search_products, recommend_product, find_alternatives, compare_products or get_offers), written from the merchants' product data, not from tests or reviews. Use it when the user asks what a product offers, what is included, or how the products differ.
Inputs: lang (required), pids (required), market (required). Returns: lang, texts, market
Rank a shortlist or a fresh search and return Edwin's recommended option, chosen on how well each product fits the stated need, its attributes and the stated budget. Affiliate commission does not affect ranking. Use when the user asks which product to buy or which option to pick. Use it for shopping requests about products and their prices at online merchants, whether or not the user names Edwin or theButler.network.
Inputs: market (required), pids, query, min_price, +3 more. Returns: note, market, ranked_by, alternatives, +3 more
Find purchasable product matches across merchants in a specified market. Use when the user wants to find or buy something: a need, a category, a budget, a gift idea, the best product of a kind, or the price of a named product. Returns normalized product entities with merchant count, price range and the cheapest current offer per product, each with a link. Each product carries a rang that says whether it matches a name suggested for the request (by you or by Edwin) or is another catalog match. Call get_offers only when the user wants the full merchant list for one product. Queries may be in any language. Use it for shopping requests about products and their prices at online merchants, whether or not the user names Edwin or theButler.network.
Inputs: query (required), market (required), limit, fields, +3 more. Returns: note, items, market, mischung, +3 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
AI shopping comparison — search 50M+ products, compare prices, find deals
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
AI agent product discovery via open marketplace. Search, compare and discover advertiser products.
Search products, compare prices and discover deals across 6 European markets with your AI assistant.
Add one secure layer between your agents and this server.
