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
8 tools
Its own safety labels
0 read-only, 8 with no label
Memory it takes
About 2,000 tokens of your AI's memory, just for its tool descriptions
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 13 Nov 2026.
Is Mandate Law: legal counsel for AI products MCP server safe?
None of the hidden-instruction wordings we know were found in its 8 tool descriptions.
0 of its 8 tools are labeled read-only; the others may change or send things.
Overall it scored 77/100 on 13 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
8 tools, in the server's own words.
check_scope
Free.
conflict_check
Free.
request_engagement
After conflict_check.
submit_intake
Only after the engagement letter is signed.
answer_open_question
Answer one of counsel's open questions (listed by get_matter).
feature_check
For engaged clients, with the human's approval (it may be billed).
get_matter
Status, counsel's open questions, feature checks, and deliverables (documents, privileged_memo, build_spec, verification_checklist, counsel_triggers).
!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 described7 warnings
!check_scope: Inputs with no description: request
!conflict_check: Inputs with no description: client_name, other_people, adverse_or_related_parties
!request_engagement: Inputs with no description: conflict_check_id
!submit_intake: Inputs with no description: matter_id, intake
!answer_open_question: Inputs with no description: matter_id, question_id
!feature_check: Inputs with no description: matter_id, change, trigger_ids, target_ship_date
!get_matter: Inputs with no description: matter_id
note
!
Tools are labeled safe or dangerous1 warning
!8 of 8 tools have no safety label (read-only or dangerous): check_scope, conflict_check, request_engagement, submit_intake, answer_open_question, feature_check, get_matter, get_counsel_triggers
note
!
Follows MCP best practices (not scored yet)2 tips (not scored)
!8 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): check_scope, conflict_check, request_engagement, submit_intake, answer_open_question, feature_check and 2 more
!8 tools don't say whether they reach outside services like the web (openWorldHint): check_scope, conflict_check, request_engagement, submit_intake, answer_open_question, feature_check and 2 more
note
✓
ConnectsConnected in 219 ms
pass
✓
Lists its toolsFound 8 tools
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
✓
Fast enoughAll good
✓Connecting took 219 ms
✓Listing tools took 46 ms
pass
–
Tools work with good inputsNot tested
–check_scope: Not run: no safety label (if you own this server, test again in owner mode)
–conflict_check: Not run: no safety label (if you own this server, test again in owner mode)
–request_engagement: Not run: no safety label (if you own this server, test again in owner mode)
–submit_intake: Not run: no safety label (if you own this server, test again in owner mode)
–answer_open_question: Not run: no safety label (if you own this server, test again in owner mode)
–feature_check: Not run: no safety label (if you own this server, test again in owner mode)
–get_matter: Not run: no safety label (if you own this server, test again in owner mode)
–get_counsel_triggers: Not run: no safety label (if you own this server, test again in owner mode)
not tested
–
Bad inputs give a clean errorNot tested
not tested
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested
–
No secrets leakedNo error messages to check
not tested
–
No known hidden instructions in tool answers (not scored yet)No tool answered, so there were no answers to read
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 Mandate Law: legal counsel for AI products, 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.