supershopping MCP server
ai.atdev/supershoppingatdev.aistreamable-httpv1.0.0Scanned
나만을 위한 AI 쇼핑 MCP — 상품을 자연어로 검색·비교·추천해 사용자의 효과적인 쇼핑을 돕습니다.
8 tools: 3 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 8
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the supershopping MCP server can do
The supershopping MCP server is published by atdev.ai, a domain the MCP Registry verified. It has 8 tools. It can create or change data (3 tools: recommend_products, recommend_outfit and initiate_checkout), but cannot delete data. 5 tools only read.
8 tools bring in text other people can write (search_products, get_product_detail, get_product_image and 5 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 3Claude Code: ask
initiate_checkout슈퍼쇼핑에서 선택한 상품의 구매로 연결 — 최저가 쇼핑몰의 구매 링크와 가격·고지를 반환.Reads text others writeNo findings
Why it is in this group
- The name "initiate_checkout" says "checkout": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑에서 선택한 상품의 구매로 연결 — 최저가 쇼핑몰의 구매 링크와 가격·고지를 반환. 언제: 사용자가 구매 의사를 보일 때("이거 살래", "구매하기"). 실제 결제는 판매처 페이지에서 일어난다. 반환: {payload: {merchant, buy_url(제휴 변환됨), price, ...}, affiliate_disclosure?, next_actions}. → buy_url을 명확한 구매 링크로 제시하고, affiliate_disclosure가 있으면 반드시 고지하라. 중고(used)는 개인 직거래이므로 안전결제/실물확인을 안내하라.
Annotations the server declares
- title: 슈퍼쇼핑 결제 시작(데모)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
recommend_outfit슈퍼쇼핑에서 어울리는 코디를 추천 (씨앗 상품 또는 의도 기반).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑에서 어울리는 코디를 추천 (씨앗 상품 또는 의도 기반). 언제: "이 코트에 어울리는 코디", "가을 데이트룩 코디" 처럼 한 벌 구성을 원할 때. 인자: product_id(씨앗 아이템, 선택), intent(의도/무드, 선택), budget(전체 예산 상한, 선택). 둘 중 하나는 필요. 반환: {seed, items:[{slot, title, min_price, reason, buy_url, thumbnail, source}], styling_reason, affiliate_disclosure?}. → 각 아이템을 buy_url 링크와 함께 제시하고, 사진은 get_product_image로 보여줘라.
Annotations the server declares
- title: 슈퍼쇼핑 코디 추천
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
recommend_products슈퍼쇼핑에서 의도·예산 기반 상품 추천 + 추천 근거.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑에서 의도·예산 기반 상품 추천 + 추천 근거. 언제: 사용자가 구체적 검색어 없이 용도/취향/예산만 말할 때("겨울 데이트룩 추천", "50만원대 가성비 노트북"). 인자: intent(용도/취향), budget(예산 상한), must_have(필수 조건). 반환: {recommendations: [{title, min_price, reason, buy_url, thumbnail, source}], affiliate_disclosure?}. → 각 추천을 buy_url 링크와 함께 제시하고, 사진은 get_product_image로 보여줘라.
Annotations the server declares
- title: 슈퍼쇼핑 상품 추천
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 5Show 5 read-only tools
analyze_market슈퍼쇼핑 카테고리 시세 분석 — 가격 분포·최저가몰·대안.Reads text others writeNo findings
Why it is in this group
- The name "analyze_market" says "analyze": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑 카테고리 시세 분석 — 가격 분포·최저가몰·대안. 언제: 사용자가 시세/적정가를 물을 때("그래픽카드 요즘 얼마", "노트북 가격대"). category는 이름(예: '노트북') 또는 ID. 반환: 가격 통계(최저/중앙/최고·분포)·최저가 쇼핑몰·대안 상품.
Annotations the server declares
- title: 슈퍼쇼핑 시장 분석
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
compare_products슈퍼쇼핑 상품 여러 개(2~5개)의 스펙·가격 비교 매트릭스 + 한 줄 결론.Reads text others writeNo findings
Why it is in this group
- The name "compare_products" says "compare": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑 상품 여러 개(2~5개)의 스펙·가격 비교 매트릭스 + 한 줄 결론. 언제: 사용자가 후보 여러 개를 견주려 할 때("이 중에 뭐가 나아?"). product_ids는 search 결과에서. 반환: {attributes: 공통 키, matrix: 상품별 값/가격, verdict: 한국어 결론}.
Annotations the server declares
- title: 슈퍼쇼핑 상품 비교
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_product_detail슈퍼쇼핑 상품의 전체 상세 — 스펙·쇼핑몰별 가격(offers)·신품/중고 교차비교.Reads text others writeNo findings
Why it is in this group
- The name "get_product_detail" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑 상품의 전체 상세 — 스펙·쇼핑몰별 가격(offers)·신품/중고 교차비교. 언제: 사용자가 한 상품을 깊이 보거나 구매 직전일 때. (product_id는 search/recommend 결과에서 얻는다) 반환: 전체 속성 + offers(쇼핑몰별 buy_url) + comparison_url + other_sources(같은 모델의 다른 소스 신품↔중고 가격 스프레드) + affiliate_disclosure(있으면 고지). → other_sources로 "같은 모델 중고는 얼마" 같은 가격차를 안내하면 좋다.
Annotations the server declares
- title: 슈퍼쇼핑 상품 상세
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_product_image슈퍼쇼핑 상품의 대표 이미지를 실제 이미지(렌더 가능)로 반환.Reads text others writeNo findings
Why it is in this group
- The name "get_product_image" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 슈퍼쇼핑 상품의 대표 이미지를 실제 이미지(렌더 가능)로 반환. 언제: 사용자가 상품 사진을 보고 싶어할 때("이 코트 보여줘"). 검색/추천 결과의 thumbnail은 URL(텍스트)이라 화면에 안 뜨므로, 시각 확인이 필요하면 이 툴로 이미지 자체를 가져온다. 반환: 이미지 콘텐츠(여러 개를 한 번에 보여주지 말고 관심 상품 위주로 호출).
Annotations the server declares
- title: 슈퍼쇼핑 상품 이미지
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_products자연어로 신품·중고 통합 상품 검색 (슈퍼쇼핑의 기본 진입점).Reads text others writeNo findings
Why it is in this group
- The name "search_products" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 자연어로 신품·중고 통합 상품 검색 (슈퍼쇼핑의 기본 진입점). 언제: 사용자가 특정 상품을 찾을 때. 예) "남성 패딩 20만원 이하", "중고 RTX 4070", "27인치 게이밍 모니터". 자동 처리: 도메인(패션/전자)·성별·가격대·속성을 질의에서 추출해 필터링. 반환: {items: [{title, min_price, key_specs, thumbnail, buy_url, source, condition, ...}], total}. → 결과 제시 시 각 buy_url을 링크로 함께 보여줘라. 사진은 get_product_image로 렌더. 추천만 원하거나 검색어가 모호하면 recommend_products를 써라.
Annotations the server declares
- title: 슈퍼쇼핑 상품 검색
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:24 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://supershopping-mcp.atdev.ai/mcp: tools/list returned 8 tools to an anonymous client, including recommend_products (write), recommend_outfit (write), initiate_checkout (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http supershopping https://supershopping-mcp.atdev.ai/mcpclaude mcp add --transport http supershopping https://supershopping-mcp.atdev.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__supershopping__search_products",
"mcp__supershopping__get_product_detail",
"mcp__supershopping__get_product_image",
"mcp__supershopping__compare_products",
"mcp__supershopping__analyze_market"
],
"ask": [
"mcp__supershopping__recommend_products",
"mcp__supershopping__recommend_outfit",
"mcp__supershopping__initiate_checkout"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as supershopping. Review it before you use it.
Capability tags behind 8 rules
- mcp__supershopping__search_products untrusted-input
- mcp__supershopping__get_product_detail untrusted-input
- mcp__supershopping__get_product_image untrusted-input
- mcp__supershopping__compare_products untrusted-input
- mcp__supershopping__recommend_products untrusted-input
- mcp__supershopping__recommend_outfit untrusted-input
- mcp__supershopping__analyze_market untrusted-input
- mcp__supershopping__initiate_checkout untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.atdev/supershopping/verify?hash=29accaec853d3d58f18a4ac4b93ec661d29155e2d13a03f18a4e49a4a43652f9" | jq -e '.changed == false'Pinned hash 29accaec853d, from Nov 10, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.atdev/supershopping/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.atdev/supershopping)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:41 UTC.
supershopping MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the supershopping MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the supershopping MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the supershopping MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the supershopping MCP server have?
- 8 tools: 3 write, 5 read. recommend_products, recommend_outfit, initiate_checkout, search_products, get_product_detail, get_product_image, compare_products and analyze_market.
Does the supershopping MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the supershopping MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the supershopping MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.