# offerhopper.ai — AI Supermarket & Drugstore Shopping Assistant for Germany (remote · mcp.offerhopper.ai)

Live prices, deals & optimal multi-stop shopping routes for German grocery & drug stores.

- Trust score: 87/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `mcp.offerhopper.ai`: 87/100 (this document), [markdown](https://verifymcp.io/servers/ai-offerhopper-mcp-german-grocery-assistant/mcp.md), [page](https://verifymcp.io/servers/ai-offerhopper-mcp-german-grocery-assistant/mcp)

## Channel facts

- Endpoint: `https://mcp.offerhopper.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 994 tokens (~110/item across 9 items; 2 tools + 7 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server?

offerhopper.ai — AI Supermarket & Drugstore Shopping… is a hosted endpoint at https://mcp.offerhopper.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-offerhopper-mcp-german-grocery-assistant 'https://mcp.offerhopper.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-offerhopper-mcp-german-grocery-assistant": {
      "url": "https://mcp.offerhopper.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-offerhopper-mcp-german-grocery-assistant": {
      "type": "http",
      "url": "https://mcp.offerhopper.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-offerhopper-mcp-german-grocery-assistant]
url = "https://mcp.offerhopper.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-offerhopper-mcp-german-grocery-assistant": {
      "type": "remote",
      "url": "https://mcp.offerhopper.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-offerhopper-mcp-german-grocery-assistant --url 'https://mcp.offerhopper.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-offerhopper-mcp-german-grocery-assistant:
    url: "https://mcp.offerhopper.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-offerhopper-mcp-german-grocery-assistant": {
      "Transport": "http",
      "Url": "https://mcp.offerhopper.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-offerhopper-mcp-german-grocery-assistant -t streamable-http -u 'https://mcp.offerhopper.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-offerhopper-mcp-german-grocery-assistant": {
      "type": "http",
      "url": "https://mcp.offerhopper.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-18 (score 87, +1)

- [security] Stability: 0.97 → pass

### 2026-09-16 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 85, +7)

- [security improvement] Judged manipulation: unverified → pass
- [functional improvement] Schema quality: unverified → good

### 2026-09-13 (score 78, −6)

- [security regression] Judged manipulation: pass → unverified
- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: good → unverified
- [functional regression] Prompt “Explain my optimization result” was removed
- [functional regression] Prompt “Plan a shopping trip” was removed
- [functional] New prompt “explain_optimization_result”
- [functional] New prompt “plan_shopping_trip”
- [functional] Server version: 1.0.2 → 1.0.3
- [cosmetic] “plan_optimal_shopping_route” reworded the description of “max_stores”

### 2026-09-11 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 82, +1)

- [security] Tool “plan_optimal_shopping_route” rewrote its description, which is the text the model reads

### 2026-09-05 (score 81, +1)

- [functional regression] Schema quality: 80 → 101
- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
- [functional] MCP protocol version: 2025-11-25 → 2026-07-28
- [functional] New tool “swap_route_item”

## MCP tools (2)

### `plan_optimal_shopping_route` (~417 tokens)

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), 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).

Input parameters:

- `end_location`: Optional destination location if not a round trip
- `hour_cost`: Time cost penalty in EUR per hour (defaults to 12.0)
- `items` (string, required): The shopping list in natural language (e.g. '3x milk, eggs, bread')
- `km_cost`: Travel cost penalty per kilometer (forced to 0.0 for bicycle/pedestrian)
- `location` (string, required): Starting location (ZIP code, city, or address in Germany)
- `max_radius_km`: Maximum search radius in kilometers (defaults: car=15km, bicycle=5km, pedestrian=2km)
- `max_stores` (integer): Maximum number of candidate stores to evaluate for the route (default: 100)
- `shopping_time_per_store`: Base shopping minutes spent per store (defaults to 10)
- `travel_mode` (string): Travel mode to use

### `swap_route_item` (~275 tokens)

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.

Input parameters:

- `alt_id` (string, required): offer_id of the alternative to swap in (from that item's 'alternatives')
- `offer_id` (string, required): offer_id of the item currently on the route (from products_to_buy)
- `share` (string, required): The share_url (or its 8-char id) returned by plan_optimal_shopping_route

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-offerhopper-mcp-german-grocery-assistant/mcp#diagnostics

## Score history

- 2026-09-21: 87
- 2026-09-20: 87
- 2026-09-19: 87
- 2026-09-18: 87
- 2026-09-17: 86
- 2026-09-16: 86
- 2026-09-15: 85
- 2026-09-14: 85
- 2026-09-13: 78
- 2026-09-12: 84
- 2026-09-11: 84
- 2026-09-10: 83
- 2026-09-09: 83
- 2026-09-08: 82
- 2026-09-07: 82
- 2026-09-06: 81
- 2026-09-05: 81
- 2026-09-04: 80
- 2026-09-03: 79
- 2026-09-02: 79
- 2026-09-01: 78
- 2026-08-31: 78
- 2026-08-30: 78
- 2026-08-29: 77
- 2026-08-28: 77
- 2026-08-27: 76
- 2026-08-26: 76
- 2026-08-25: 74
- 2026-08-24: 74
- 2026-08-23: 73

## Common questions

### What is the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server?

offerhopper.ai — AI Supermarket & Drugstore Shopping… is an MCP server listed in the public MCP registry as ai.offerhopper.mcp/german-grocery-assistant. Live prices, deals & optimal multi-stop shopping routes for German grocery & drug stores. This page covers its hosted endpoint (https://mcp.offerhopper.ai/mcp).

### Is the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server safe to use?

offerhopper.ai — AI Supermarket & Drugstore Shopping… scores 87 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server expose?

offerhopper.ai — AI Supermarket & Drugstore Shopping… exposes 2 tools: plan_optimal_shopping_route, swap_route_item. Their descriptions and schemas cost roughly 692 tokens of context every time the server is loaded.

### Does the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server require authentication?

No. We connected to offerhopper.ai — AI Supermarket & Drugstore Shopping… without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server still maintained?

offerhopper.ai — AI Supermarket & Drugstore Shopping… is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.offerhopper.ai/mcp
- Website: https://offerhopper.ai/blog/en/ai-grocery-shopping-assistant
- Changelog RSS feed: https://verifymcp.io/servers/ai-offerhopper-mcp-german-grocery-assistant/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-offerhopper-mcp-german-grocery-assistant/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-offerhopper-mcp-german-grocery-assistant/mcp