Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

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.

0 this week 85 Trust /100

Last scanned (12 hours ago)

Scores higher than 86% of remote servers

Reachable. Last reached 21 Nov 2026.

Category E-commerce

Trust breakdown (7 categories)

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
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
What we tested

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 →

Changelog

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
Diagnostics

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
MCP tools · 9 exposed · ~801 tokens

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 →

Tool Tokens
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.

NameTypeReqDescription
emailstringyesthe buyer's email given on create_order_intent
intent_idstringyesthe order intent id, oi-<16 hex>
offer_idstringyesthe offer to accept, as get_offers lists it

No output schema declared.

No examples provided.

compare_drinks ~61

Compare two to ten products side by side, field by field, each value with its source page.

NameTypeReqDescription
record_idsarrayyestwo to ten record ids, e.g. ["es-bev:000123", "fr-bev:000456"]

No output schema declared.

No examples provided.

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.

NameTypeReqDescription
buyerobjectyesthe buying organisation and its email (kept private; the key to read offers and accept one)
marketstringyesdelivery market (country)
needed_bystring–YYYY-MM-DD
notestring–optional note to the makers
quantitystringyesquantity with its unit, e.g. 600 bottles (75 cl)
record_idsarrayyesone to ten record ids to order, e.g. ["es-bev:000123"]

No output schema declared.

No examples provided.

find_producer ~64

Find a maker and its products across every open node, with the maker's name as each source wrote it.

NameTypeReqDescription
nodestring–optional node id, e.g. es-bev
producerstringyesthe maker's name, or part of it

No output schema declared.

No examples provided.

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.

NameTypeReqDescription
emailstringyesthe buyer's email given on create_order_intent
intent_idstringyesthe order intent id from create_order_intent, oi-<16 hex>

No output schema declared.

No examples provided.

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.

NameTypeReqDescription
record_idstringyesthe record id, <node>:<6 digits>, e.g. es-bev:000123

No output schema declared.

No examples provided.

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).

NameTypeReqDescription
record_idstringyesthe record id, <node>:<6 digits>, e.g. es-bev:000123

No output schema declared.

No examples provided.

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 ~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.

NameTypeReqDescription
categorystring–optional category to keep: beer, wine, spirits, cider_perry or rtd (ready-to-drink)
limitinteger–optional number of results, 1 to 100
nodestring–optional node id, e.g. es-bev
querystringyesname, style, origin or category

No output schema declared.

No examples provided.

Install

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

# add to Claude Code
claude mcp add --transport http ai-agent-bev-bev-door 'https://mcp.bev-buyer.ai/mcp'
Common questions

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.