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
7 tools
Its own safety labels
3 read-only, 2 labeled as deleting or destroying, 2 labeled as changing things
Memory it takes
About 1,500 tokens of your AI's memory, just for its tool descriptions
Tools that look alike
1 pair of tools with nearly the same description, so the AI may pick the wrong one
Speed
Average answer in our test: 112 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 Docs MD: markdown workspace for AI agents MCP server safe?
None of the hidden-instruction wordings we know were found in its 7 tool descriptions.
Its error messages showed no secrets or internal details.
3 of its 7 tools are labeled read-only; the others may change or send things.
Overall it scored 93/100 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.
!update_share and delete_share have nearly the same description (67% of their words are shared; the only difference: "replace", "content", "link" vs "delete", "permanently"), so an AI may not know which to pick
note
✓
ConnectsConnected in 273 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 7 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
✓whoami: Answered with an error, probably because of our sample input: error: agent_key_required This tool needs agent_key. Call register_agent once, keep the key it returns, and pass it as agent_key.
✓read_share: Answered with an error, probably because of our sample input: error: not_found No such document. It may have expired or been deleted.
✓list_my_shares: Answered with an error, probably because of our sample input: error: agent_key_required This tool needs agent_key. Call register_agent once, keep the key it returns, and pass it as agent_key.
–register_agent: Not run: labeled as changing data
–share_markdown: Not run: labeled as changing data
–update_share: Not run: labeled dangerous
–delete_share: Not run: labeled dangerous
pass
✓
Bad inputs give a clean errorAll good
✓whoami: Refused wrong type for "agent_key" with a clear error
✓read_share: Refused missing required input "id" with a clear error
✓read_share: Refused wrong type for "id" with a clear error
✓list_my_shares: Refused wrong type for "agent_key" with a clear error
pass
✓
Fast enoughAll good
✓Connecting took 273 ms
✓Listing tools took 137 ms
✓Average tool answer: 112 ms
✓whoami: Slowest tool: whoami (140 ms)
pass
✓
No secrets leakedChecked 7 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 7 answers from 3 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 Docs MD: markdown workspace for AI agents, 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.