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
6 tools
Its own safety labels
6 read-only
Memory it takes
About 1,300 tokens of your AI's memory, just for its tool descriptions
Largest answer
About 8 KB in our test
Speed
Average answer in our test: 307 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 InterfaceDelta MCP server safe?
None of the hidden-instruction wordings we know were found in its 6 tool descriptions.
Its error messages showed no secrets or internal details.
All 6 of its tools are labeled read-only.
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
6 tools, in the server's own words.
get_passportread-only
Read a Passport someone shared with you, by the observation ID in its link (/passport/ /observations/ ).
check_toolread-only
Read the stored facts and effect classes for one MCP tool, with a signature; never a verdict.
search_atlasread-only
Search the public service atlas; omit query to browse.
get_atlas_entryread-only
Read an atlas entry, labels and publicly displayed AI readings.
lookup_domainread-only
Read-only public domain summary, matching host and subdomains, up to 10 services per page.
list_changesread-only
Read-only recorded atlas changes strictly after since, oldest first.
!check_tool: Inputs with no description: endpoint, tool, since
note
✓
ConnectsConnected in 364 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 6 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_passport: Answered with an error, probably because of our sample input: Input validation error: Invalid arguments for tool get_passport: data/observationId must match pattern "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-…
✓check_tool: Answered with an error, probably because of our sample input: {"ok":false,"error":{"code":"INTERNAL_ERROR","message":"The requested data could not be read."}} {"ok":false,"error":{"code":"INTERNAL_ERRO…
✓search_atlas: Worked (705 ms)
✓get_atlas_entry: Answered with an error, probably because of our sample input: {"ok":false,"error":{"code":"NOT_FOUND","message":"This record was not found. Call its list tool to find an accessible ID."}} {"ok":false,"…
✓lookup_domain: Answered with an error, probably because of our sample input: {"ok":false,"error":{"code":"INVALID_DOMAIN","message":"Invalid domain."}} {"ok":false,"error":{"code":"INVALID_DOMAIN","message":"Invalid …
✓list_changes: Answered with an error, probably because of our sample input: Input validation error: Invalid arguments for tool list_changes: data/since must match pattern "^\d{4}-\d\d-\d\dT\d\d:\d\d:\d\d(?:\.\d{1,3}…
pass
✓
Bad inputs give a clean errorAll good
✓get_passport: Refused missing required input "observationId" with a clear error
✓get_passport: Refused wrong type for "observationId" with a clear error
✓check_tool: Refused missing required input "endpoint" with a clear error
✓check_tool: Refused wrong type for "endpoint" with a clear error
✓search_atlas: Refused wrong type for "cursor" with a clear error
✓get_atlas_entry: Refused missing required input "target" with a clear error
✓get_atlas_entry: Refused wrong type for "target" with a clear error
✓lookup_domain: Refused missing required input "domain" with a clear error
No secrets leakedChecked 16 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 17 answers from 6 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 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.