MCP 服务器

offerhopper.ai — AI Supermarket & Drugstore Shopping Assistant for Germany

ai.offerhopper.mcp/german-grocery-assistant
电商与零售 公开且可连接 MCP 2025-11-25

此 MCP 可以做什么

Provides live German grocery and drugstore prices, deals, and multi-stop shopping route optimization.

plan_optimal_shopping_route
Plan optimal grocery and drug store shopping trip
Plans the optimal shopping trip for a given list and starting location in Germany. Answers 'where should I go to buy this list, and is the trip worth it?' — not 'what's on offer near me'. Matches each item on the list to the best current offer across German supermarkets and drug stores (REWE, Aldi, Lidl, Penny, Netto, Norma, Edeka, DM, Rossmann, Mueller, Globus), then computes the cheapest realistic route by weighing product prices against travel distance and shopping time. Returns the chosen store(s), the per-item picks with live prices, the trip's savings and a worth-it Supports car, bicycle, and pedestrian travel modes. For corridor trips (A-to-B), supply 'end_location' to route stores along the way. Pricing note: 'price' is the standard shelf price available to all shoppers (do NOT say discounts require an app). 'app_credit' is optional wallet cashback (e.g. REWE Bonus: plus €0.50 into wallet). 'app_price' is an app-exclusive checkout price (e.g. Lidl Plus).
只读 可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['items', 'location'], 'properties': {'items': {'type': 'string', 'description': "The shopping list in natural language (e.g. '3x milk, eggs, bread')"}, 'km_cost': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Travel cost penalty per kilometer (forced to 0.0 for bicycle/pedestrian)'}, 'location': {'type': 'string', 'description': 'Starting location (ZIP code, city, or address in Germany)'}, 'hour_cost': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Time cost penalty in EUR per hour (defaults to 12.0)'}, 'max_stores': {'type': 'integer', 'default': 100, 'description': 'Maximum number of candidate stores to evaluate for the route (default: 100)'}, 'travel_mode': {'enum': ['car', 'bicycle', 'pedestrian'], 'type': 'string', 'default': 'car', 'description': 'Travel mode to use'}, 'end_location': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'default': None, 'description': 'Optional destination location if not a round trip'}, 'max_radius_km': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'default': None, 'description': 'Maximum search radius in kilometers (defaults: car=15km, bicycle=5km, pedestrian=2km)'}, 'shopping_time_per_store': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'default': None, 'description': 'Base shopping minutes spent per store (defaults to 10)'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
swap_route_item
Swap an item on a shopping route
Swaps one item's chosen offer on an existing shopping route (from a prior plan_optimal_shopping_route result) for one of its alternatives, then returns the RECOMPUTED route with corrected costs and the honest worth-it verdict. Use this to correct a poor pick (e.g. the engine matched a soup hen instead of a roasting chicken) or to take a cheaper/better option the agent spotted in the item's 'alternatives'. The alternative may be at the SAME store or at ANOTHER store ALREADY ON THE ROUTE — it must be the same item category, and its store must already be a stop (no new stores; for that, call plan_optimal_shopping_route again). Keys on stable offer ids: pass the current item's offer_id and the target alternative's offer_id (both taken verbatim from the prior response's products_to_buy / alternatives). The shared route (share_url) is updated in place so the interactive map reflects the swap.
可访问外部资源
输入模式
{'type': 'object', 'required': ['share', 'offer_id', 'alt_id'], 'properties': {'share': {'type': 'string', 'description': 'The share_url (or its 8-char id) returned by plan_optimal_shopping_route'}, 'alt_id': {'type': 'string', 'description': "offer_id of the alternative to swap in (from that item's 'alternatives')"}, 'offer_id': {'type': 'string', 'description': 'offer_id of the item currently on the route (from products_to_buy)'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
已更改
plan_optimal_shopping_route
2026年9月27日 02:51
已添加
swap_route_item
2026年9月17日 07:57
已添加
plan_optimal_shopping_route
2026年9月17日 07:57