GAIP Integration & Protocol Agent
REMOTE · WWW.GAIPAGENTS.COM
Behind Check and GAIP Watch, and Diagnose: A2A, MCP and OpenAPI checks with a dated change log.
Available components
Last scanned (12 hours ago)
Scores higher than 83% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Security
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
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: this server exposes a tool marked destructive (gaip_watch_remove) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated. View diagnostics → Unverified
- 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
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability87
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3134 tokens (~184/item across 17 items; 13 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
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 15 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 (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: this server exposes a tool marked destructive (gaip_watch_remove) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated.
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.
- 10 Nov 26 +1
- Stability: 0.97 → pass security
- 9 Nov 26 −1
- Stability: pass → 0.97 functional
- 8 Nov 26 +1
- Stability: 0.97 → pass security
- 7 Nov 26 −1
- 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
- 5 Nov 26 +1
- Stability: 0.97 → pass security
- 4 Nov 26 −1
- Stability: pass → 0.97 functional
- 27 Oct 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://www.gaipagents.com/mcp/agents/integration-protocol
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/agents/integration-protocol | Verified | 200 | |
| http (plaintext) | http://www.gaipagents.com/mcp/agents/integration-protocol | HTTPS enforced | 308 | https://www.gaipagents.com/mcp/agents/integration-protocol |
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 →
check_agent_conformance Check an AI agent or MCP server ~334
Use this when asked to check an AI agent or MCP server: does it work, is it reachable, is its card valid ("check this agent", "is this MCP server up?"). Pass just its `url`. Returns READY / FIXES_NEEDED / NO_AGENT_CARD / UNREACHABLE with fixes and a receipt. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| data_classification | string | – | PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data. |
| declared_identity | string | – | Optional: the name the agent claims. |
| expected_endpoint | string | – | Optional: the endpoint you expect; a different primary endpoint is reported as ENDPOINT_DRIFT. |
| intended_task | string | – | VERIFY_BEFORE_CALL: what you intend to delegate. |
| metadata | object | – | Alternative to url: the agent card or MCP/OpenAPI document itself. |
| mode | string | – | CONFORMANCE (default) checks the interface; VERIFY_BEFORE_CALL returns task-specific evidence about `target` for `intended_task`. |
| protocol | string | – | Counterparty protocol. Inferred from metadata when omitted, otherwise MCP. |
| source_url | string | – | Optional: where `metadata` was published, used only to resolve relative endpoints. Never fetched. |
| target | – | – | VERIFY_BEFORE_CALL: the counterparty URL or reference. |
| url | string | – | Public https link to an agent, its A2A agent card, MCP server description or OpenAPI document. GAIP fetches, validates and reach-tests it. Use instead of metadata. |
No output schema declared.
{"url":"https://www.gaipagents.com/.well-known/agent-card.json"}{"metadata":{"name":"GAIP Broker","protocolVersion":"2025-06-18","tools":[],"url":"https://www.gaipagents.com/mcp"}} gaip_check_permission May my agent fetch this? ~185
Use this before your agent fetches a page ("may my agent fetch this?"). Pass the `url` and your `agent` token. Reads robots.txt (RFC 9309), AI-preference lines, RSL, tdmrep.json and llms.txt; returns ALLOWED, DISALLOWED, NO_RULE or UNKNOWN, the rule quoted, the time and a signature. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | Your agent's user-agent token as robots.txt names it, e.g. GPTBot or ClaudeBot (a full User-Agent string also works). Default * (any crawler without its own rules). |
| url | string | yes | The public https URL your agent wants to fetch. |
| user_agent | string | – | Alternative to agent: your agent's full User-Agent string. |
No output schema declared.
{"agent":"GPTBot","url":"https://www.gaipagents.com/test-range"} gaip_compare_supplier_snapshots What changed between two versions ~291
Use this when asked what changed between two versions of an agent card, MCP server description or OpenAPI document ("did this API break?"). Pass `prior` and `current`. Returns each change as BREAKING / NON_BREAKING / INFO with migration notes and a receipt. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| continuity_handle | object | – | Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones. |
| counterparty_id | string | – | Name or URL of the agent/service. Optional. |
| current | object | yes | The later version, same kind as `prior`. |
| data_classification | string | – | PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data. |
| episode_id | string | – | Optional: your own id to group related calls. |
| independent_operator_id | string | – | Optional: your operator id (recorded as a claim, not verified). |
| prior | object | yes | The earlier version: agent card, MCP server description, OpenAPI document or snapshot. |
| protocol | string | – | Counterparty protocol. Inferred from metadata when omitted, otherwise MCP. |
| synthetic | boolean | – | Optional: true marks a test call. |
| task_class | string | – | Optional: short name of the task, e.g. weather_forecast. |
No output schema declared.
{"counterparty_id":"example-weather-agent","current":{"capabilities":{"streaming":true},"name":"Weather Agent","protocolVersion":"0.3.0","security":[{"bearer":[]}],"securitySchemes":{"bearer":{"scheme":"bearer","type":"http"}},"skills":[{"id":"forecast","name":"Forecast"}],"url":"https://weather.example.com/v2/a2a","version":"2.0.0"},"prior":{"capabilities":{"streaming":true},"name":"Weather Agent","protocolVersion":"0.3.0","skills":[{"id":"forecast","name":"Forecast"},{"id":"alerts","name":"Severe weather alerts"}],"url":"https://weather.example.com/a2a","version":"1.4.0"}} gaip_diagnose_integration_failure Why did my agent call fail? ~309
Use this when an agent, MCP or API call failed ("why did my call fail?", "what does this 429 mean?"). Pass the `failure` ({code, detail}) or the raw error text. Returns the likely cause, when and how to retry, fix steps and a receipt. GAIP touches no other system. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| continuity_handle | object | – | Optional: the continuity_handle from an earlier GAIP result; links this call to your earlier ones. |
| counterparty_id | string | – | Name or URL of the agent/service. Optional. |
| data_classification | string | – | PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data. |
| episode_id | string | – | Optional: your own id to group related calls. |
| failure | object | yes | The failure: {code, detail?, http_status?}, e.g. {"code": 429, "detail": "Too Many Requests; Retry-After: 20"}. |
| independent_operator_id | string | – | Optional: your operator id (recorded as a claim, not verified). |
| protocol | string | – | Counterparty protocol. Inferred from metadata when omitted, otherwise MCP. |
| synthetic | boolean | – | Optional: true marks a test call. |
| task_class | string | – | Optional: short name of the task, e.g. weather_forecast. |
No output schema declared.
{"counterparty_id":"example-weather-agent","failure":{"code":429,"detail":"HTTP 429 Too Many Requests; Retry-After: 20"}} gaip_manifest_changes What changed recently (manifest log) ~154
Use this when asked which MCP servers or agents changed recently ("what changed this week?"). Optional `since` (RFC 3339), `target_id`, `limit` (max 100). Returns the Observatory's hash-chained log of manifest changes: before/after hashes, neutral facts, receipts. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Optional: maximum entries (1-100). |
| since | string | – | Optional: RFC 3339 time, e.g. 2026-09-01T00:00:00Z. |
| target_id | string | – | Optional: an Observatory target id (obs_...). |
No output schema declared.
{"limit":20,"since":"2026-09-01T00:00:00Z"} gaip_observatory_capture Save an agent's declarations now ~145
Use this to save a dated record of what a public MCP server or A2A agent card declares now. Pass its `url`. GAIP reads it once (robots.txt respected, never tools/call), re-reads it daily and returns the capture id, time and SHA-256 hashes. Not an assessment. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| protocol | string | – | Optional; inferred from the URL (a /.well-known/agent-card.json path is A2A). |
| url | string | yes | Public https URL of the MCP endpoint or the A2A agent card. |
No output schema declared.
{"url":"\u003cpublic https URL of the MCP endpoint or A2A agent card to save\u003e"} gaip_observatory_lookup Look up an MCP server's or agent's history ~142
Use this when asked about an MCP server's or agent's history ("has this server changed?", "was it up last week?"). Pass its `url` or `name`. Returns dated facts the Agent Observatory observed: status history, manifest hash, conformance codes, change log. Not an assessment. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Optional: server or agent name to search for. |
| target_id | string | – | Optional: an Observatory target id (obs_...). |
| url | string | – | Public URL of the MCP server or agent to look up. |
No output schema declared.
{"url":"https://huggingface.co/mcp"} gaip_supplier_reliability Why is my supplier failing? ~313
Use this when a supplier agent or API you depend on started failing ("did something change on their side?"). Pass its `supplier_url` and the `failure`. Returns the diagnosis plus changes GAIP observed around then (correlated in time, not causation), with receipts. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| card | object | – | Optional supplier card / server description you integrated against. |
| counterparty_id | string | – | Optional: name of the supplier. |
| data_classification | string | – | PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data. |
| failure | object | – | {code, detail?, http_status?} as for gaip_diagnose_integration_failure. |
| failure_started_at | string | – | Optional: RFC 3339 time the failures started. |
| failures | array | – | Optional: several failures, each {code, detail}. |
| lookback_days | integer | – | Optional: days of GAIP observations to look back over. |
| protocol | string | – | Omit to infer it from card, transport or the supplier URL path (else UNKNOWN). |
| supplier_url | string | yes | Public https URL of the supplier's agent card, MCP server or API. |
| task_class | string | – | Optional: short name of the task, e.g. weather_forecast. |
| transport | string | – | Optional transport you used (e.g. streamable-http, sse, GRPC). |
No output schema declared.
{"failure":{"code":404,"detail":"Not Found"},"failure_started_at":"2026-09-27T12:00:00Z","supplier_url":"https://weather.example.com/.well-known/agent-card.json"} gaip_tools_changed_since Has this MCP server changed? ~235
Use this before connecting to an MCP server: did its tools change since your `since` date? Pass its `url`, optionally your tools/list `tools` or a digest. Returns dates, change classes, stored hashes and whether yours match the latest GAIP observed. Facts, not a verdict. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| since | string | – | Your approval date (RFC 3339 or YYYY-MM-DD): changes recorded since then. |
| target_id | string | – | Optional: an Observatory target id (obs_...). |
| tool_digests | array | – | Per-tool digests in the DRAFT MCP SEP-2636 form (may change). |
| tools | array | – | The `tools` array from your own tools/list; GAIP hashes it and compares. |
| tools_digest | string | – | A SHA-256 (64 hex) of the tool list you approved, as GAIP reported it. |
| url | string | – | The MCP endpoint (or A2A agent card) URL, exactly as you connect to it. |
No output schema declared.
{"since":"2026-09-01","url":"https://huggingface.co/mcp"} gaip_watch_events Read watch change events ~128
Use this when asked what changed on a watched agent or service. Pass your `continuity_handle` and optionally a `watch_id`. Returns recent change events: verdict before and after, a change summary, the receipt and webhook delivery status. Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| continuity_handle | object | yes | The continuity_handle from an earlier GAIP result; proves you own these watches. |
| limit | integer | – | Optional: maximum events to return. |
| watch_id | string | – | The watch_id returned by gaip_watch_register. |
No output schema declared.
{"continuity_handle":{"continuity_id":"\u003ccontinuity_handle.continuity_id returned by any GAIP tool\u003e","token":"\u003ccontinuity_handle.token returned by any GAIP tool\u003e"},"limit":10,"watch_id":"\u003cwatch_id from gaip_watch_register\u003e"} gaip_watch_list List my watches ~92
Use this when asked which agents or services you are watching. Pass your `continuity_handle`. Returns each watch's kind, target, last verdict, last and next check and webhook endpoint (never the secret). Free, read-only, no account; inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| continuity_handle | object | yes | The continuity_handle from an earlier GAIP result; proves you own these watches. |
No output schema declared.
{"continuity_handle":{"continuity_id":"\u003ccontinuity_handle.continuity_id returned by any GAIP tool\u003e","token":"\u003ccontinuity_handle.token returned by any GAIP tool\u003e"}} gaip_watch_register Watch an agent or MCP server for changes ~337
Use this when asked to keep an eye on an agent or MCP server ("tell me if it changes or goes down"). Pass the `continuity_handle` from any GAIP result, `kind` and `target_url`. GAIP re-checks every 24 hours (3 free watches), receipts each change and can call your webhook. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| continuity_handle | object | yes | The continuity_handle from an earlier GAIP result; proves you own these watches. |
| data_classification | string | – | PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data. |
| interval_hours | integer | – | Hours between checks: 24 minimum on the free tier; 1 for DELIVERY_SLA. |
| kind | string | yes | AGENT_READINESS (agent URL), SUPPLIER_CARD (published card), DELIVERY_TERMS (terms_id) or DELIVERY_SLA (terms_id plus sla terms). |
| sla | object | – | DELIVERY_SLA only: service-level terms checked on every observation, any of min_uptime_pct, max_latency_ms, required_fields (JSON key paths), freshness_field + max_age_seconds; optional uptime_window… |
| target_url | string | – | Public https URL (AGENT_READINESS, SUPPLIER_CARD). No query string. |
| terms_id | string | – | DELIVERY_TERMS or DELIVERY_SLA: terms_id from witness_register_terms. |
| webhook_url | string | – | Optional: your own public https endpoint for signed change events. |
No output schema declared.
{"continuity_handle":{"continuity_id":"\u003ccontinuity_handle.continuity_id returned by any GAIP tool\u003e","token":"\u003ccontinuity_handle.token returned by any GAIP tool\u003e"},"interval_hours":24,"kind":"AGENT_READINESS","target_url":"https://weather.example.com/"} gaip_watch_remove Remove a watch ~108
Use this when asked to stop watching an agent or service. Pass your `continuity_handle` and the `watch_id`. Its stored events are deleted; retained receipts stay verifiable. Free, no account; records a GAIP receipt only. Inputs must be public and non-personal.
| Name | Type | Req | Description |
|---|---|---|---|
| continuity_handle | object | yes | The continuity_handle from an earlier GAIP result; proves you own these watches. |
| watch_id | string | yes | The watch_id returned by gaip_watch_register. |
No output schema declared.
{"continuity_handle":{"continuity_id":"\u003ccontinuity_handle.continuity_id returned by any GAIP tool\u003e","token":"\u003ccontinuity_handle.token returned by any GAIP tool\u003e"},"watch_id":"\u003cwatch_id from gaip_watch_register\u003e"} How do I install the GAIP Integration & Protocol Agent MCP server?
GAIP Integration & Protocol Agent is a hosted endpoint at https://www.gaipagents.com/mcp/agents/integration-protocol, 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
claude mcp add --transport http tjcgraham-rgb-gaip-integration-protocol 'https://www.gaipagents.com/mcp/agents/integration-protocol'
What is the GAIP Integration & Protocol Agent MCP server?
GAIP Integration & Protocol Agent is an MCP server listed in the public MCP registry as io.github.tjcgraham-rgb/gaip-integration-protocol. Behind Check and GAIP Watch, and Diagnose: A2A, MCP and OpenAPI checks with a dated change log. This page covers its hosted endpoint (https://www.gaipagents.com/mcp/agents/integration-protocol).
Is the GAIP Integration & Protocol Agent MCP server safe to use?
GAIP Integration & Protocol Agent scores 83 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 Integration & Protocol Agent MCP server expose?
GAIP Integration & Protocol Agent exposes 13 tools: check_agent_conformance, gaip_watch_register, gaip_watch_list, gaip_watch_remove, gaip_watch_events, and 8 more. Their descriptions and schemas cost roughly 2,773 tokens of context every time the server is loaded.
Does the GAIP Integration & Protocol Agent MCP server require authentication?
No. We connected to GAIP Integration & Protocol Agent without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the GAIP Integration & Protocol Agent MCP server still maintained?
GAIP Integration & Protocol Agent 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 Integration & Protocol Agent MCP server?
VerifyMCP ran 12 checks on GAIP Integration & Protocol Agent, 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 GAIP Integration & Protocol Agent: 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.