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.
Available components
Last scanned (10 hours ago)
Scores higher than 94% of remote servers
Reachable. Last reached 5 Nov 2026.
Category E-commerce
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. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability84
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 997 tokens (~110/item across 9 items; 2 tools + 7 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Sept 26 0
- Tool “plan_optimal_shopping_route” rewrote its description, which is the text the model reads security
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 14 Sept 26 0
- Judged manipulation: unverified → pass ▲ security
- Schema quality: unverified → good ▲ functional
- 13 Sept 26 0
- Judged manipulation: pass → unverified ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: good → unverified ▼ functional
- Prompt “Explain my optimization result” was removed ▼ functional
- 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 functional
- “plan_optimal_shopping_route” reworded the description of “max_stores” cosmetic
- 7 Sept 26 0
- Tool “plan_optimal_shopping_route” rewrote its description, which is the text the model reads security
- 5 Sept 26 0
- 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” functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://mcp.offerhopper.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=offerhopper.ai | CN=WE1,O=Google Trust Services,C=US | 9 Sept 2026 | 8 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | ed34fbdfe354821613be95ec015dd670 |
| SANs: offerhopper.ai, *.offerhopper.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.offerhopper.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814, 3799 | 8, 8 | Verified |
| offerhopper.ai. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.offerhopper.ai/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.offerhopper.ai/mcp | HTTPS enforced | 301 | https://mcp.offerhopper.ai/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
plan_optimal_shopping_route Plan optimal grocery and drug store shopping trip ~420
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).
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | 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 | yes | 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 |
Structured output declared, but exposes no named fields.
No examples provided.
swap_route_item Swap an item on a shopping route ~275
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.
| Name | Type | Req | Description |
|---|---|---|---|
| alt_id | string | yes | offer_id of the alternative to swap in (from that item's 'alternatives') |
| offer_id | string | yes | offer_id of the item currently on the route (from products_to_buy) |
| share | string | yes | The share_url (or its 8-char id) returned by plan_optimal_shopping_route |
Structured output declared, but exposes no named fields.
No examples provided.
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.
remote · mcp.offerhopper.ai
claude mcp add --transport http ai-offerhopper-mcp-german-grocery-assistant 'https://mcp.offerhopper.ai/mcp'
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 695 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 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the offerhopper.ai — AI Supermarket & Drugstore Shopping… MCP server?
VerifyMCP ran 13 checks on offerhopper.ai — AI Supermarket & Drugstore Shopping…, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.