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
4 tools
Its own safety labels
4 read-only
Memory it takes
About 1,100 tokens of your AI's memory, just for its tool descriptions
Largest answer
About 5 KB in our test
Speed
Average answer in our test: 152 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 meirinho.com.br, leitura para agentes MCP server safe?
None of the hidden-instruction wordings we know were found in its 4 tool descriptions.
Its error messages showed no secrets or internal details.
All 4 of its tools are labeled read-only.
Overall it scored 89/100 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.
!Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described4 warnings
!search: Inputs with no description: query, collection
!list: Inputs with no description: collection, limit, use
!get: Inputs with no description: url, slug, collection
!get_comparison_row: Inputs with no description: model, versus, use, slugs, query, fields
note
!
Follows MCP best practices (not scored yet)2 tips (not scored)
!Very common tool names: search, list, get. Next to other servers' tools the AI may mix them up; a short prefix helps (like "github_search" instead of "search").
!2 tools answer with structured data but don't declare its shape (outputSchema): search, list. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
note
✓
ConnectsConnected in 738 ms
pass
✓
Lists its toolsFound 4 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
✓search: Worked (156 ms)
✓list: Worked (170 ms)
✓get: Answered with an error, probably because of our sample input: {"found":false,"lang":"pt","tool":"get","note":"Não está publicado."}
✓get_comparison_row: Answered with an error, probably because of our sample input: {"found":false,"lang":"pt","tool":"get_comparison_row","note":"Não está publicado.","rows":[]}
pass
✓
Bad inputs give a clean errorAll good
✓search: Refused missing required input "query" with a clear error
✓search: Refused wrong type for "query" with a clear error
✓list: Refused missing required input "collection" with a clear error
✓list: Refused wrong type for "collection" with a clear error
✓get: Refused wrong type for "lang" with a clear error
✓get_comparison_row: Refused wrong type for "lang" with a clear error
pass
✓
Tools work together3 chains working
✓search → get: get found what search returned (url = "/ia/modelos/gpt-chat-latest/")
✓list → get: get found what list returned (url = "/mercado/deepnote-agent-initiative/")
✓search → get_comparison_row: get_comparison_row found what search returned (slugs = "gpt-chat-latest")
pass
✓
Fast enoughAll good
✓Connecting took 738 ms
✓Listing tools took 146 ms
✓Average tool answer: 152 ms
✓list: Slowest tool: list (170 ms)
pass
✓
No secrets leakedChecked 13 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 18 answers from 4 tools: none of the hidden-instruction wordings we know were found. New wordings can get past this check.
pass
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.