agent-bev
REMOTE · MCP.BEV-BUYER.AI · 2 COMPONENTS
The world's largest agentic B2B hub for beer, wine and spirits. Powered by CUVEE. Trade only.
Available components
Last scanned (12 hours ago)
Scores higher than 86% of remote servers
Reachable. Last reached 21 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 Security71
- 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 check failed: the endpoint is reachable over plaintext HTTP. See how to fix → View diagnostics → Fail
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 929 tokens (~103/item across 9 items; 9 tools + 0 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 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.
- 13 Nov 26 0
- Server version: 0.2.6 → 0.2.8 functional
- 11 Nov 26 +1
- Stability: 0.97 → pass security
- 10 Nov 26 −1
- Stability: pass → 0.97 functional
- 9 Nov 26 +1
- Stability: 0.97 → pass security
- 8 Nov 26 −1
- Stability: pass → 0.97 functional
- 7 Nov 26 +1
- Stability: 0.97 → pass security
- 6 Nov 26 −1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 5 Nov 26 +1
- Stability: 0.97 → pass security
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 21 Nov 2026 · Probed https://mcp.bev-buyer.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=bev-buyer.ai | CN=WE1,O=Google Trust Services,C=US | 27 Sept 2026 | 26 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 2e5b9a976a388dc50e16c470226fa689 |
| SANs: bev-buyer.ai, mcp.bev-buyer.ai, *.mcp.bev-buyer.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 secure
Validation of mcp.bev-buyer.ai. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| bev-buyer.ai. | DS published | 2371 | 13 | Verified |
| mcp.bev-buyer.ai. | Verified address RRset verified with the apex keys |
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 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'none'; img-src 'self'; style-src 'self' 'unsafe-inline'; script-src 'self'; connect-src https://formspree.io; form-action https://formspree.io; base-uri 'none'; frame-ancestors 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.bev-buyer.ai/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.bev-buyer.ai/mcp | Served over HTTP | 200 |
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 →
accept_offer Accept offer ~115
Accept one offer and place the order through the Bourse. Accepting is one x402 paid call (HTTP 402 with the payment offer until paid): it settles and signs the order. The goods are paid between the two companies on the offer's own terms.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | the buyer's email given on create_order_intent | |
| intent_id | string | yes | the order intent id, oi-<16 hex> |
| offer_id | string | yes | the offer to accept, as get_offers lists it |
No output schema declared.
No examples provided.
compare_drinks Compare drinks ~61
Compare two to ten products side by side, field by field, each value with its source page.
| Name | Type | Req | Description |
|---|---|---|---|
| record_ids | array | yes | two to ten record ids, e.g. ["es-bev:000123", "fr-bev:000456"] |
No output schema declared.
No examples provided.
create_order_intent Create order intent ~191
Place an order intent for one to ten records (quantity, delivery market, optional date and note, the buyer's organisation and email). The Bourse routes it to each maker; verified makers answer with offers, and a maker's own Brand Agent address comes back with the routing. The email stays private: it is the buyer's key to read offers and accept one.
| Name | Type | Req | Description |
|---|---|---|---|
| buyer | object | yes | the buying organisation and its email (kept private; the key to read offers and accept one) |
| market | string | yes | delivery market (country) |
| needed_by | string | – | YYYY-MM-DD |
| note | string | – | optional note to the makers |
| quantity | string | yes | quantity with its unit, e.g. 600 bottles (75 cl) |
| record_ids | array | yes | one to ten record ids to order, e.g. ["es-bev:000123"] |
No output schema declared.
No examples provided.
find_producer Find producer ~64
Find a maker and its products across every open node, with the maker's name as each source wrote it.
| Name | Type | Req | Description |
|---|---|---|---|
| node | string | – | optional node id, e.g. es-bev |
| producer | string | yes | the maker's name, or part of it |
No output schema declared.
No examples provided.
get_offers Get offers ~77
Read the makers' offers on an order intent, and the order once placed. By the buyer's email given on create_order_intent.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | the buyer's email given on create_order_intent | |
| intent_id | string | yes | the order intent id from create_order_intent, oi-<16 hex> |
No output schema declared.
No examples provided.
get_order_route Get order route ~62
Get the maker's or distributor's trade channel to order a product, as the record states it. Never a consumer channel.
| Name | Type | Req | Description |
|---|---|---|---|
| record_id | string | yes | the record id, <node>:<6 digits>, e.g. es-bev:000123 |
No output schema declared.
No examples provided.
get_record Get record ~72
Read one product in full by record_id: every field with its source page, reader and state; its CUVEE; its claim status; the signed record (JWS).
| Name | Type | Req | Description |
|---|---|---|---|
| record_id | string | yes | the record id, <node>:<6 digits>, e.g. es-bev:000123 |
No output schema declared.
No examples provided.
list_nodes List nodes ~33
List the countries on the record: each node's door, languages, state and, for an open node, its counts.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
search_drinks Search drinks ~126
Find beers, wines, spirits, ciders and ready-to-drink drinks by name, style, origin or category across every open country node. Returns record ids with each record's CUVEE.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | optional category to keep: beer, wine, spirits, cider_perry or rtd (ready-to-drink) |
| limit | integer | – | optional number of results, 1 to 100 |
| node | string | – | optional node id, e.g. es-bev |
| query | string | yes | name, style, origin or category |
No output schema declared.
No examples provided.
How do I install the agent-bev MCP server?
agent-bev is a hosted endpoint at https://mcp.bev-buyer.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.bev-buyer.ai
claude mcp add --transport http ai-agent-bev-bev-door 'https://mcp.bev-buyer.ai/mcp'
What is the agent-bev MCP server?
agent-bev is an MCP server listed in the public MCP registry as ai.agent-bev/bev-door. The world's largest agentic B2B hub for beer, wine and spirits. Powered by CUVEE. Trade only. This page covers its hosted endpoint (https://mcp.bev-buyer.ai/mcp).
Is the agent-bev MCP server safe to use?
agent-bev scores 85 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 agent-bev MCP server expose?
agent-bev exposes 9 tools: search_drinks, get_record, find_producer, list_nodes, compare_drinks, and 4 more. Their descriptions and schemas cost roughly 801 tokens of context every time the server is loaded.
Does the agent-bev MCP server require authentication?
No. We connected to agent-bev without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the agent-bev MCP server still maintained?
agent-bev is still listed as active in the MCP registry. We last reached this channel on 21 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 agent-bev MCP server?
VerifyMCP ran 13 checks on agent-bev, 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.