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
1 read-only, 1 labeled as changing things
Memory it takes
About 380 tokens of your AI's memory, just for its tool descriptions
Speed
Average answer in our test: 118 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 Deadline Desk 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.
1 of its 2 tools are labeled read-only; the others may change or send things.
Overall it scored 88/100 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.
lookup_policy
Look up a US retailer's published return, price adjustment, warranty, or cancellation policy with quoted source text and a TRACE receipt.
get_receiptread-only
Fetch a public receipt from a prior Deadline Desk policy lookup.
!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 described2 warnings
!lookup_policy: Inputs with no description: kind
!get_receipt: Inputs with no description: receipt_id
note
!
Follows MCP best practices (not scored yet)2 tips (not scored)
!1 tool not labeled read-only doesn't say whether running it twice is safe (idempotentHint): lookup_policy
!2 tools don't say whether they reach outside services like the web (openWorldHint): lookup_policy, get_receipt
note
✓
ConnectsConnected in 448 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.
pass
✓
Tools work with good inputsAll good
✓get_receipt: Answered with an error, probably because of our sample input: {"error":"not_found"}
–lookup_policy: Not run: labeled as changing data
pass
✓
Bad inputs give a clean errorAll good
✓get_receipt: Refused missing required input "receipt_id" with a clear error
✓get_receipt: Refused wrong type for "receipt_id" with a clear error
pass
✓
Fast enoughAll good
✓Connecting took 448 ms
✓Listing tools took 99 ms
✓Average tool answer: 118 ms
✓get_receipt: Slowest tool: get_receipt (118 ms)
pass
✓
No secrets leakedChecked 3 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 3 answers from 1 tool: none of the hidden-instruction wordings we know were found. New wordings can get past this check.
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.