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
2 tools
Its own safety labels
2 read-only
Memory it takes
About 250 tokens of your AI's memory, just for its tool descriptions
Largest answer
About 2.8 KB in our test
Speed
Average answer in our test: 143 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 14 Nov 2026.
Is 장보기 (Jangbogi) MCP server safe?
None of the hidden-instruction wordings we know were found in its 2 tool descriptions.
Its error messages showed no secrets or internal details.
All 2 of its tools are labeled read-only.
Overall it scored 83/100 on 14 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
2 tools, in the server's own words.
get_planread-only
미리 계산해 둔 이번 주 저녁 식단과 마켓컬리 장바구니(plan.json)를 돌려준다.
list_optionsread-only
고를 수 있는 인원·예산 단계·끼니 수 범위, 예산 단계 규칙, 파일 주소 규칙, 현재 발행본 정보(회차·주차·묶음 수), 고지를 돌려준다.
!Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described1 warning
!get_plan: Inputs with no description: people, budget_per_meal, meals, include_recipes
note
!
Bad inputs give a clean error1 warning
!get_plan: Accepted wrong type for "people" without complaining
and 1 more
note
!
Follows MCP best practices (not scored yet)2 tips (not scored)
!2 tools don't say whether they reach outside services like the web (openWorldHint): get_plan, list_options
!2 tools answer with structured data but don't declare its shape (outputSchema): get_plan, list_options. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
note
✓
ConnectsConnected in 988 ms
pass
✓
Lists its toolsFound 2 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.
No secrets leakedChecked 1 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 4 answers from 2 tools: none of the hidden-instruction wordings we know were found. New wordings can get past this check.
pass
–
Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (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.