ChatAd 손님 (chatad.kr)
REMOTE · MCP.GMP.AI
Try ChatAd without login: ad readiness check, site analysis, campaign drafts, sign-up.
Available components
Last scanned (1 hour ago)
Scores higher than 45% of remote servers
Reachable. Last reached 25 Oct 2026.
Category Marketing and SEO
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 Security51
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- 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 Usability66
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1358 tokens (~150/item across 9 items; 9 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 Management3
- Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 67% of tool parameters carry a description.Partial
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
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.
- 25 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 24 Oct 26 58
First indexed and scored.
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 25 Oct 2026 · Probed https://mcp.gmp.ai/chatad?guest=1
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=gmp.ai | CN=WE1,O=Google Trust Services,C=US | 10 Sept 2026 | 9 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | f7446258ec85706b1392a1b76091bb0f |
| SANs: gmp.ai, mcp.gmp.ai, *.mcp.gmp.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 insecure
Validation of mcp.gmp.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| gmp.ai. | absent | 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=31536000; includeSubDomains |
| x-content-type-options | nosniff |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.gmp.ai/chatad?guest=1 | Verified | 200 | |
| http (plaintext) | http://mcp.gmp.ai/chatad?guest=1 | Inconclusive | 405 |
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 →
about_chatad ~64
ChatAd 가 무엇이고 무엇을 할 수 있는지, 로그인 없이 쓸 수 있는 것과 가입 뒤에 쓸 수 있는 것, 가입하는 방법을 돌려준다. 처음 들어왔으면 이것부터 부른다. 하루 한도에 들지 않는다.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
analyze_site ~115
웹사이트를 읽어 제목·설명·주요 내용·광고 목표 후보·문맥 힌트 후보와 광고별 최소 일예산을 돌려준다. 캠페인 초안을 만들기 전에 부른다. 🔴 로그인 없이 MCP 세션마다 50회, 세션 번호가 없으면 하루 3회(이름을 밝힌 봇은 5회)까지다.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | 분석할 웹사이트 주소. https:// 는 빼도 된다 |
No output schema declared.
No examples provided.
check_ad_readiness ~105
웹사이트 첫 화면을 읽어 광고 전환 측정 준비가 되어 있는지 본다(Google 태그 관리자 · GA4 · Meta 픽셀 · 사이트 응답). 🔴 로그인 없이 MCP 세션마다 50회, 세션 번호가 없으면 하루 3회(이름을 밝힌 봇은 5회)까지다.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | 분석할 웹사이트 주소. https:// 는 빼도 된다 |
No output schema declared.
No examples provided.
check_signup ~53
device 방식에서 사용자가 승인했는지 본다. 승인됐으면 access_token 이 온다. 아직이면 status 가 pending 이니 interval 초 뒤에 다시 부른다.
| Name | Type | Req | Description |
|---|---|---|---|
| device_code | string | yes | – |
No output schema declared.
No examples provided.
complete_signup ~101
email_code 방식의 마지막 단계. 사용자가 불러 준 6자리 코드로 가입·로그인을 마치고 access_token 을 받는다. 그 토큰을 Authorization: Bearer 로 붙여 회원 MCP(https://mcp.gmp.ai/chatad, ?guest 없이)를 부른다.
| Name | Type | Req | Description |
|---|---|---|---|
| client_name | string | – | – |
| code | string | yes | 메일로 받은 6자리 숫자 |
| string | yes | – |
No output schema declared.
No examples provided.
draft_campaign ~193
웹사이트와 하루 총 예산으로 OpenAI·Google·Meta 광고 캠페인 초안(예산 배분 · 핵심 메시지 · 키워드나 문맥 힌트 · 광고 문구)을 만든다. 🔴 초안만 만든다. 광고주 계정에는 아무것도 만들지 않는다. 🔴 예산은 사용자가 말한 금액만 쓴다. 🔴 로그인 없이 MCP 세션마다 50회, 세션 번호가 없으면 하루 3회(이름을 밝힌 봇은 5회)까지다.
| Name | Type | Req | Description |
|---|---|---|---|
| daily_budget_krw | integer | yes | 하루 총 예산(원). 사용자가 말한 금액 그대로 |
| media | array | – | 초안을 만들 광고. 안 주면 셋 다 |
| url | string | yes | 분석할 웹사이트 주소. https:// 는 빼도 된다 |
No output schema declared.
No examples provided.
get_guides ~50
광고를 시작할 때 필요한 준비물과 절차를 적은 가이드 목록(OpenAI·Google·Meta 광고 시작 가이드 등)을 돌려준다. 하루 한도에 들지 않는다.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_plans ~69
요금제와 결제 방법을 돌려준다. 🔴 금액이 확정되지 않았으면 prices_confirmed 가 false 로 온다. 그때는 금액을 지어내지 말고 「확정 전」이라고 안내한다. 하루 한도에 들지 않는다.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
start_signup ~184
사용자 대신 ChatAd 가입을 시작한다. 🔴 사용자가 가입하겠다고 답한 뒤에만 부른다. 방법이 둘이다. method=email_code: 사용자 메일로 6자리 코드가 간다. 사용자에게 코드를 물어 complete_signup 에 넣는다. method=device: 확인 주소와 짧은 코드가 온다. 사용자에게 그 주소를 열어 로그인·승인하라고 안내하고, check_signup 으로 승인됐는지 본다. 어느 쪽이든 약관 동의와 본인 확인은 사용자가 직접 한다.
| Name | Type | Req | Description |
|---|---|---|---|
| client_name | string | – | 이 에이전트의 이름(예: Claude, ChatGPT, Grok, Meta AI). 승인 화면에 보인다 |
| string | – | method=email_code 일 때 필요한 사용자 이메일 | |
| method | string | yes | – |
No output schema declared.
No examples provided.
How do I install the ChatAd 손님 (chatad.kr) MCP server?
ChatAd 손님 (chatad.kr) is a hosted endpoint at https://mcp.gmp.ai/chatad?guest=1, 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.gmp.ai
claude mcp add --transport http kr-chatad-chatad-guest 'https://mcp.gmp.ai/chatad?guest=1'
What is the ChatAd 손님 (chatad.kr) MCP server?
ChatAd 손님 (chatad.kr) is an MCP server listed in the public MCP registry as kr.chatad/chatad-guest. Try ChatAd without login: ad readiness check, site analysis, campaign drafts, sign-up. This page covers its hosted endpoint (https://mcp.gmp.ai/chatad?guest=1).
Is the ChatAd 손님 (chatad.kr) MCP server safe to use?
ChatAd 손님 (chatad.kr) scores 58 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 ChatAd 손님 (chatad.kr) MCP server expose?
ChatAd 손님 (chatad.kr) exposes 9 tools: about_chatad, get_plans, get_guides, check_ad_readiness, analyze_site, and 4 more. Their descriptions and schemas cost roughly 934 tokens of context every time the server is loaded.
Does the ChatAd 손님 (chatad.kr) MCP server require authentication?
No. We connected to ChatAd 손님 (chatad.kr) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the ChatAd 손님 (chatad.kr) MCP server still maintained?
ChatAd 손님 (chatad.kr) is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.