Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.
Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
On their server. What you send to it goes to them.
What you need
Nothing: it answered without a login
Tools
5 tools
Its own safety labels
4 read-only, 1 labeled as changing things
Memory it takes
About 3,400 tokens of your AI's memory, just for its tool descriptions
Speed
Average answer in our test: 80 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From the daily test on 15 Nov 2026.
Is Korea Sets — Korean-version K-beauty sets MCP server safe?
None of the hidden-instruction wordings we know were found in its 5 tool descriptions.
Its error messages showed no secrets or internal details.
4 of its 5 tools are labeled read-only; the others may change or send things.
Overall it scored 93/100 on 15 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
Its source code and packages.
What a tool quietly does behind the scenes, such as writing a file or calling another service.
Instructions hidden inside live tool answers. We only look for those in tool descriptions.
Hidden instructions worded in a way our list doesn't know yet.
Tools that could change something. Those are read, never run.
It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.
What it can do
5 tools, in the server's own words.
list_setsread-only
Use when: the user asks which Korean-version K-beauty sets they can get, what is in a set, its Korean promo dates or its estimated delivered total; call it fir…
estimate_totalread-only
Use when: the user asks what one parcel of given sets costs delivered to the US, Canada or Japan, duties and shipping included.
plan_boxesread-only
Use when: estimate_total says the parcel is over the weight limit, or the user asks how to ship many sets most cheaply.
clarify_requestread-only
Use when: the user's request is vague (no set named, no delivery country, only a city, a budget without a currency, or a budget that does not say whether shipp…
request_quote
Use when: the user agreed to send their email address and the listed sets, and wants a confirmed delivered total (request="order") or an email when a set is av…
!estimate_total: Inputs with no description: items, ship_country
!plan_boxes: Inputs with no description: items, ship_country
!clarify_request: Inputs with no description: items, bundle_sku, quantity, budget, trigger, substitution
!request_quote: Inputs with no description: items, quantity, ship_country, request
note
✓
ConnectsConnected in 238 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 5 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
pass
✓
Tools work with good inputsAll good
✓list_sets: Answered with an error, probably because of our sample input: { "status": "paused", "tool": "list_sets", "message": "Korea Sets is a pilot and is paused right now. No request was taken and nothing was …
✓estimate_total: Answered with an error, probably because of our sample input: { "status": "paused", "tool": "estimate_total", "message": "Korea Sets is a pilot and is paused right now. No request was taken and nothing…
✓plan_boxes: Answered with an error, probably because of our sample input: { "status": "paused", "tool": "plan_boxes", "message": "Korea Sets is a pilot and is paused right now. No request was taken and nothing was…
✓clarify_request: Answered with an error, probably because of our sample input: { "status": "paused", "tool": "clarify_request", "message": "Korea Sets is a pilot and is paused right now. No request was taken and nothin…
–request_quote: Not run: labeled as changing data
pass
✓
Bad inputs give a clean errorAll good
✓estimate_total: Refused missing required input "items" with a clear error
✓estimate_total: Refused wrong type for "items" with a clear error
✓plan_boxes: Refused missing required input "items" with a clear error
✓plan_boxes: Refused wrong type for "items" with a clear error
✓clarify_request: Refused wrong type for "items" with a clear error
pass
✓
Fast enoughAll good
✓Connecting took 238 ms
✓Listing tools took 102 ms
✓Average tool answer: 80 ms
✓list_sets: Slowest tool: list_sets (118 ms)
pass
✓
No secrets leakedChecked 9 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 9 answers from 4 tools: none of the hidden-instruction wordings we know were found. New wordings can get past this check.
pass
✓
Follows MCP best practices (not scored yet)Tool names, safety labels and tool list size follow the MCP guide
pass
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested
Show this score on GitHub
Free for every server in the directory. Paste this into your README: the badge always shows the newest score, from the daily test, a test on our website or a Monitor test.
Coming soon: reviews from people who use Korea Sets — Korean-version K-beauty sets, signed in with GitHub, one per person. Reviews never change the score.
Is this your server? Get an alert the moment it breaks.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.