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
3 tools
Its own safety labels
3 read-only
Memory it takes
About 1,300 tokens of your AI's memory, just for its tool descriptions
Largest answer
About 0.6 KB in our test
Speed
Average answer in our test: 43 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 DiscoverSeniorBenefits MCP server safe?
None of the hidden-instruction wordings we know were found in its 3 tool descriptions.
Its error messages showed no secrets or internal details.
All 3 of its tools are labeled read-only.
Overall it scored 88/100 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
3 tools, in the server's own words.
find_programs_by_zipread-only
List the federal, state, and county senior-benefit programs that apply where a person lives, from their 5-digit ZIP code or their city and state.
run_eligibility_scanread-only
Check which senior-benefit programs a person likely qualifies for, using a deterministic rule engine tied to cited .gov sources — no AI guessing.
get_program_detailsread-only
Full public details for one program by its id (ids come from find_programs_by_zip or run_eligibility_scan): description, cited government source, how to apply,…
!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
!run_eligibility_scan: Inputs with no description: household_size, homeownership, disability_status, is_blind, is_us_citizen
note
✓
ConnectsConnected in 272 ms
pass
✓
Lists its toolsFound 3 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
✓find_programs_by_zip: Answered with an error, probably because of our sample input: Invalid arguments: 1 validation error for FindProgramsInput Value error, Give a 5-digit ZIP code, or a city together with its state (e.g. c…
✓get_program_details: Worked (42 ms)
–run_eligibility_scan: Not run: labeled read-only, but its name starts with "run", which usually means it changes something. Skipped to be safe: if it only reads, a clearer name helps AI apps too, or test again with --owner
pass
✓
Bad inputs give a clean errorAll good
✓find_programs_by_zip: Refused wrong type for "zip" with a clear error
✓get_program_details: Refused missing required input "program_id" with a clear error
✓get_program_details: Refused wrong type for "program_id" with a clear error
No secrets leakedChecked 4 error messages: no secrets or internal details
pass
✓
No known hidden instructions in tool answers (not scored yet)Read 5 answers from 2 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.