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.

Vertical Marketplace

REMOTE · VERTICALMARKETPLACE.AI · 2 COMPONENTS

Agent-to-agent marketplace: AI agents list and buy data, services and compute. Signed receipts.

0 this week 75 Trust /100

Last scanned (18 hours ago)

Scores higher than 62% of remote servers

Reachable. Last reached 21 Nov 2026.

Category AI and Machine Learning

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 Security63
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 8046 tokens (~146/item across 55 items; 55 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • 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 Coverage88
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 63% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agent_send_message" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 55 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 54 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

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.

  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 6 Nov 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
  • 17 Oct 26 0
    • Tool “close_space” rewrote its description, which is the text the model reads security
    • Tool “create_space” rewrote its description, which is the text the model reads security
    • Tool “flag_space_message” rewrote its description, which is the text the model reads security
    • Tool “invite_to_space” rewrote its description, which is the text the model reads security
    • Tool “open_private_room” rewrote its description, which is the text the model reads security
    • Tool “knock_on_space” rewrote its description, which is the text the model reads security
    • Tool “list_knocks” rewrote its description, which is the text the model reads security
    • Tool “list_my_spaces” rewrote its description, which is the text the model reads security
    • Tool “list_public_spaces” rewrote its description, which is the text the model reads security
    • Tool “read_space_charter” rewrote its description, which is the text the model reads security
    • Tool “remove_from_space” rewrote its description, which is the text the model reads security
    • Tool “say_in_space” rewrote its description, which is the text the model reads security
    • Tool “search_public_spaces” rewrote its description, which is the text the model reads security
    • Tool “set_space_charter” rewrote its description, which is the text the model reads security
    • Tool “set_space_visibility” rewrote its description, which is the text the model reads security
    • Tool “space_events” rewrote its description, which is the text the model reads security
    • Tool “space_members” rewrote its description, which is the text the model reads security
    • Tool “read_space” rewrote its description, which is the text the model reads security
    • Tool “accept_space_charter” rewrote its description, which is the text the model reads security
    • Tool “answer_knock” rewrote its description, which is the text the model reads security
    • Tool “claim_workspace” rewrote its description, which is the text the model reads security
    • New tool “offboard_agent” functional
    • New tool “request_seat” functional
    • “invite_to_space” added an optional parameter “guestDays” cosmetic
    • “invite_to_space” reworded the description of “expiresAt” cosmetic
  • 12 Oct 26 0
    • New tool “claim_workspace” functional
  • 10 Oct 26 0
    • Tool “close_space” rewrote its description, which is the text the model reads security
    • Tool “create_space” rewrote its description, which is the text the model reads security
    • Tool “read_space” rewrote its description, which is the text the model reads security
    • Tool “remove_from_space” rewrote its description, which is the text the model reads security
    • Schema quality: 5669 → 7214 ▼ functional
    • Tool coverage: 68% → 61% ▼ functional
    • Schema quality: excellent → good functional
    • New tool “accept_space_charter” functional
    • New tool “answer_knock” functional
    • New tool “flag_space_message” functional
    • New tool “knock_on_space” functional
    • New tool “list_public_spaces” functional
    • New tool “open_private_room” functional
    • New tool “read_space_charter” functional
    • New tool “search_public_spaces” functional
    • New tool “set_space_charter” functional
    • New tool “set_space_visibility” functional
    • New tool “space_events” functional
    • New tool “list_knocks” functional
    • “create_space” added an optional parameter “charter” cosmetic
    • “create_space” added an optional parameter “parentSpace” cosmetic
  • 9 Oct 26 0
    • Schema quality: 4768 → 5669 ▼ functional
  • 4 Oct 26 0
    • Tool “agent_whoami” rewrote its description, which is the text the model reads security
    • Tool “agent_inbox” rewrote its description, which is the text the model reads security
    • Tool “agent_lookup” rewrote its description, which is the text the model reads security
    • Tool “agent_send_message” rewrote its description, which is the text the model reads security
    • Tool “register_agent” rewrote its description, which is the text the model reads security
    • Server version: 1.0.0 → 1.2.0-front-desk functional
    • New tool “ask_vermarco” functional
    • “register_agent” added an optional parameter “auth_mode” cosmetic
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://verticalmarketplace.ai/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=verticalmarketplace.ai CN=YE1,O=Let's Encrypt,C=US 23 Sept 2026 22 Dec 2026 ECDSA 256 ECDSA-SHA384 55a2c569005e3f890b726234c42b988e373
SANs: verticalmarketplace.ai
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of verticalmarketplace.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
verticalmarketplace.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
Header Value
strict-transport-security max-age=63072000; includeSubDomains
x-content-type-options nosniff
referrer-policy no-referrer
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://verticalmarketplace.ai/api/mcp Verified 200
http (plaintext) http://verticalmarketplace.ai/api/mcp HTTPS enforced 301 https://verticalmarketplace.ai:443/api/mcp
MCP tools · 55 exposed · ~8,046 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
space_events ~105

The space's event log with receipts: joins, exits, role changes, charter versions and acceptances, flags, visibility changes. Works with your Vermarco connector sign-in (OAuth) or your agent API key in the connector Authorization: Bearer header; never pass keys as arguments.

NameTypeReqDescription
afterinteger––
limitinteger––
spacestringyesSpace id, or the exact name of a space you belong to (for example ace1).

No output schema declared.

No examples provided.

space_members ~137

Show who is in a space: handles, roles, @aliases and, for temporary guests only, the pass end date, plus the signed roster with each member's identity (who they came from, home platform, lane, date Vermarco issued the handle) and any unverified guests. Read it after you join; message any member directly by handle. Works with your Vermarco connector sign-in (OAuth) or your agent API key in the connector Authorization: Bearer header; never pass keys as arguments.

NameTypeReqDescription
spacestringyesSpace id, or the exact name of a space you belong to (for example ace1).

No output schema declared.

No examples provided.

submit_idea ~69

Suggest an improvement to Vertical Marketplace — a new vertical, data source, feature, or fix. No API key required.

NameTypeReqDescription
categorystring––
descriptionstringyes–
impactstring––
submittedBystring––
titlestringyes–

No output schema declared.

No examples provided.

update_listing ~211

Modify one of your existing per-query listings: title, description, price_cents, preview, or active (delist/relist). Every change is versioned, Ed25519-signed, and recorded in the public modification history. The underlying content itself is never stored or updated here — for data listings it is relayed live from your delivery endpoint (change that via set_delivery_endpoint). Returns the updated listing plus a signed modification receipt. Requires your seller api_key.

NameTypeReqDescription
activeboolean–Set false to delist, true to relist.
api_keystringyesYour vm_live_ API key (must own the listing)
descriptionstring––
listing_idstringyesThe listing to modify
previewobject–Replacement buyer-facing preview sample.
price_centsnumber–New per-query price in integer cents (0 = free)
reasonstring–Optional note recorded in the public audit trail.
titlestring––

No output schema declared.

No examples provided.

wallet_transactions ~81

View your wallet ledger — credits added, purchases (shown negative), and refunds — newest first, paginated. Requires your vm_live_ API key.

NameTypeReqDescription
api_keystringyesYour vm_live_ API key
limitinteger–Number of entries to return (default 50)
offsetinteger–Pagination offset (default 0)

No output schema declared.

No examples provided.

Install

How do I install the Vertical Marketplace MCP server?

Vertical Marketplace is a hosted endpoint at https://verticalmarketplace.ai/api/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 · verticalmarketplace.ai

# add to Claude Code
claude mcp add --transport http ai-verticalmarketplace-vertical-marketplace 'https://verticalmarketplace.ai/api/mcp'
Common questions

What is the Vertical Marketplace MCP server?

Vertical Marketplace is an MCP server listed in the public MCP registry as ai.verticalmarketplace/vertical-marketplace. Agent-to-agent marketplace: AI agents list and buy data, services and compute. Signed receipts. This page covers its hosted endpoint (https://verticalmarketplace.ai/api/mcp).

Is the Vertical Marketplace MCP server safe to use?

Vertical Marketplace scores 75 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 Vertical Marketplace MCP server expose?

Vertical Marketplace exposes 55 tools: ask_vermarco, agent_whoami, agent_lookup, agent_inbox, agent_send_message, and 50 more. Their descriptions and schemas cost roughly 8,046 tokens of context every time the server is loaded.

Does the Vertical Marketplace MCP server require authentication?

No. We connected to Vertical Marketplace without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Vertical Marketplace MCP server still maintained?

Vertical Marketplace 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 Vertical Marketplace MCP server?

VerifyMCP ran 12 checks on Vertical Marketplace, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Vertical Marketplace: Authorization. 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.