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.

GAIP — evidence on AI agents before and after you call them

REMOTE · WWW.GAIPAGENTS.COM

GAIP keeps an independent, dated record of what AI agents, MCP servers and online shops publish.

0 this week 89 Trust /100

Last scanned (22 hours ago)

Scores higher than 96% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Security

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 Security80
  • 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
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability85
  • 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
  • Context-footprint check failed: tool/resource definitions use about 1808 tokens (~200/item across 9 items; 5 tools + 4 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Tools include usage examples.Pass
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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 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.

  • 21 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 20 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 18 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 17 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 16 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 15 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
  • 14 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads 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://www.gaipagents.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.gaipagents.com CN=YR1,O=Let's Encrypt,C=US 20 Nov 2026 18 Feb 2027 RSA 2048 SHA256-RSA 629394bb10f8e4e1d662f4be4ac796c3b6f
SANs: *.gaipagents.com, gaipagents.com
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of www.gaipagents.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
gaipagents.com. 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
content-security-policy default-src 'self'; style-src 'self' 'unsafe-inline'; img-src 'self' data:; connect-src 'self'; frame-ancestors 'none'; base-uri 'none'; form-action 'none'
x-content-type-options nosniff
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=(), payment=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://www.gaipagents.com/mcp Verified 200
http (plaintext) http://www.gaipagents.com/mcp HTTPS enforced 308 https://www.gaipagents.com/mcp
MCP tools · 5 exposed · ~1,551 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
gaip_check ~291

Use this when asked whether an AI agent, MCP server or API works or has changed, e.g. before adding or paying it. Pass its `url`. Returns a verdict, fixes, dated history when observed, and a receipt. With `agent` (e.g. GPTBot): may your bot fetch it (robots.txt, AI-crawler rules)? Free, read-only, no account; inputs must be public and non-personal.

NameTypeReqDescription
agentstring–Optional: ask "may my agent fetch this url?" instead. Your agent's user-agent token, e.g. GPTBot; GAIP reads the site's robots.txt and AI-permission files (gaip_check_permission).
continuity_handleobject–Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones (needed to see or remove your watches later).
intended_taskstring–Optional: what you plan to hand it, e.g. 'weather forecast for London'. Adds task-specific evidence.
urlstringyesPublic https link to the agent, its A2A agent card, MCP server endpoint or OpenAPI document. GAIP fetches, validates and reach-tests it; an MCP endpoint gets a read-only handshake (initialize, tools/…
verboseboolean–Optional: true returns the full result with every underlying field. Default: a short answer.

No output schema declared.

{"url":"https://www.gaipagents.com/.well-known/agent-card.json"}
gaip_diagnose ~278

Use this when an agent, MCP or API call failed. Paste the `error` text and/or `http_status`; add the service `url` if known. Returns the cause, the exact fix (e.g. the missing argument) and retry_after_seconds; `keep_receipt: true` adds a dated receipt. Free, read-only, no account; inputs must be public and non-personal.

NameTypeReqDescription
continuity_handleobject–Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones (needed to see or remove your watches later).
errorstring–The error you got, as text: HTTP status line, JSON-RPC/A2A/MCP error or message. Give this and/or http_status.
http_statusinteger–Optional: the HTTP status code you got, e.g. 429.
keep_receiptboolean–Optional: true keeps a dated GAIP receipt of this answer and returns a continuity handle. Default: GAIP keeps no record of the task (usage is counted without its content).
urlstring–Optional: public https URL of the agent, MCP server or API that failed.
verboseboolean–Optional: true returns the full result with every underlying field. Default: a short answer.

No output schema declared.

{"error":"HTTP 429 Too Many Requests; Retry-After: 20","http_status":429}
gaip_verify ~453

Use this when asked whether a service delivered what was promised or whether cited pages contain the quoted text. Pass `citations`, or a service `url` (+ `checks`, the `result` you got), or `claims` with `observations`. Returns a result per item. Free, no account; only delivery keeps a record. Inputs must be public and non-personal.

NameTypeReqDescription
checksarray–Optional (delivery): what a good response is, e.g. [{"id": "http_status_in", "allowed": [200]}, {"id": "json_parses"}]. Default: HTTP 200 and a non-empty body.
citationsarray–Citations to check: each {url, quote?} or just a URL. GAIP fetches each page once (robots.txt respected) and looks for the quote.
claimsarray–Claims to record about `url`: each a sentence or {id, text}. Each is compared with the `observations` you supply; without them it stays UNTESTED.
continuity_handleobject–Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones (needed to see or remove your watches later).
keep_receiptboolean–Optional: true keeps a dated GAIP receipt of this answer and returns a continuity handle. Default: GAIP keeps no record of the task (usage is counted without its content).
metadataobject–Optional (claims): the published agent card, MCP or OpenAPI document.
observationsarray–Optional (claims): what you saw, each {claim_id, result: PASS|FAIL, detail}.
resultobject–Optional (delivery): the response you received. Omitted: GAIP fetches the service URL now (public replay).
terms_idstring–Optional (delivery): terms_id from an earlier registration, instead of url.
urlstring–Claims: the agent or supplier they are about. Delivery: the public https service URL that should deliver.
verboseboolean–Optional: true returns the full result with every underlying field. Default: a short answer.

No output schema declared.

{"citations":[{"quote":"GAIP","url":"https://www.gaipagents.com/"}]}
gaip_watch ~208

Use this when asked to keep an eye on an agent or MCP server, or to be alerted when it changes. Pass its `url`: returns feed links and its latest dated changes; add `webhook_url` for a free watch (checked every 24 h, signed webhook on change). Free, no account; with a webhook it records a watch. Inputs must be public and non-personal.

NameTypeReqDescription
continuity_handleobject–Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones (needed to see or remove your watches later).
urlstringyesPublic https URL of the MCP server endpoint or agent (card) to follow. No query string.
verboseboolean–Optional: true returns the full result with every underlying field. Default: a short answer.
webhook_urlstring–Optional: your own public https endpoint. GAIP then registers a watch and POSTs a signed event when the result changes.

No output schema declared.

{"url":"https://www.gaipagents.com/mcp"}
second_look_check ~321

Use this when a shopper is about to buy something an AI suggested, or asks if a price or stock claim is right. Pass the product page `url` and the `claim`. Returns what the page showed beside what the claim said, and a signed, dated receipt. Second Look by GAIP. Free, no account, no affiliate links; inputs must be public and non-personal.

NameTypeReqDescription
claimstring–What the shopper was told, in plain words, e.g. "89 GBP, in stock, size M". Only the price, stock and variant are kept; the rest is discarded.
continuity_handleobject–Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones (needed to see or remove your watches later).
currencystring–ISO currency, e.g. GBP (optional).
in_stockboolean–Claimed stock (optional).
mandate_refstring–Optional: your own reference to the shopper's mandate for this purchase. Kept only as a keyed hash (mandate_sha256) on the receipt, never in clear.
pricestring–Claimed price, e.g. "89.00" (optional).
urlstringyesPublic https link to the product page on the shop's own site.
variantstring–Claimed size, colour or option (optional).
verboseboolean–Optional: true returns the full result with every underlying field. Default: a short answer.

No output schema declared.

{"claim":"24 GBP, in stock","url":"https://www.gaipagents.com/test-range/shop/products/demo-mug"}
Install

How do I install the GAIP — evidence on AI agents before and after you call them MCP server?

GAIP — evidence on AI agents before and after you call them is a hosted endpoint at https://www.gaipagents.com/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 · www.gaipagents.com

# add to Claude Code
claude mcp add --transport http tjcgraham-rgb-gaip-broker 'https://www.gaipagents.com/mcp'
Common questions

What is the GAIP — evidence on AI agents before and after you call them MCP server?

GAIP — evidence on AI agents before and after you call them is an MCP server listed in the public MCP registry as io.github.tjcgraham-rgb/gaip-broker. GAIP keeps an independent, dated record of what AI agents, MCP servers and online shops publish. This page covers its hosted endpoint (https://www.gaipagents.com/mcp).

Is the GAIP — evidence on AI agents before and after you call them MCP server safe to use?

GAIP — evidence on AI agents before and after you call them scores 89 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 GAIP — evidence on AI agents before and after you call them MCP server expose?

GAIP — evidence on AI agents before and after you call them exposes 5 tools: gaip_check, gaip_watch, gaip_diagnose, gaip_verify, second_look_check. Their descriptions and schemas cost roughly 1,551 tokens of context every time the server is loaded.

Does the GAIP — evidence on AI agents before and after you call them MCP server require authentication?

No. We connected to GAIP — evidence on AI agents before and after you call them without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the GAIP — evidence on AI agents before and after you call them MCP server still maintained?

GAIP — evidence on AI agents before and after you call them 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 GAIP — evidence on AI agents before and after you call them MCP server?

VerifyMCP ran 13 checks on GAIP — evidence on AI agents before and after you call them, 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.