QAmcp

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

NewYour score can change any day. QAmcp Monitor keeps testing your server and emails you when it breaks. Free for 1 server.See what Monitor does →

Directory / Verificate MCP

Verificate MCP

Q: Is Verificate MCP server safe?

QAmcp's test on 10 Nov 2026: None of the hidden-instruction wordings we know were found in its 5 tool descriptions. Its error messages showed no secrets or internal details. All 5 of its tools are labeled read-only. Overall it scored 70/100 on 10 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.

by verificate.ai · https://mcp.verificate.ai/mcp

Merge gate for AI-written code: deterministic vetoes plus a Claude Haiku 5.5 review. No signup.

5 tools✓ all read-only✓ no account neededPricing: not listed

Visit website

70 /100

FAIL

12 of 12 checks · 10 Nov 2026

Test it now for current results

At a glance

Runs where: On their server. What you send to it goes to them.
What you need: Nothing: it answered without a login
Tools: 5 tools
Its own safety labels: 5 read-only
Memory it takes: About 2,100 tokens of your AI's memory, just for its tool descriptions
Largest answer: About 20.1 KB in our test
Speed: Average answer in our test: 4.4 s

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 our latest test, 10 Nov 2026.

Is Verificate MCP server safe?

None of the hidden-instruction wordings we know were found in its 5 tool descriptions.
Its error messages showed no secrets or internal details.
All 5 of its tools are labeled read-only.
Overall it scored 70/100 on 10 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.

What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection

Known security advisories

None found in GitHub Security Advisories on 10 Nov 2026.

That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.

What it can do

5 tools, in the server's own words.

validate_artifactread-only

Deterministic production-readiness gate for AI-built systems.

validate_ai_outputread-only

The merge gate for ANY AI-written output — code, documentation, reports, emails, configs: returns a binary approve/reject verdict with veto power — e.g.

validate_planread-only

The gate for PLANS, designs and specs — run BEFORE any code is written, the cheapest place to catch a bad design.

analyze_coderead-only

Advisory deep-dive on existing code — scores and findings, deliberately NO pass/fail verdict, so it never blocks an agent.

generate_coderead-only

Generate code and gate it in one step: an LLM writes the implementation, then the same protection engine as validate_ai_output vets it — retrying generation wh…

Test results

Safe mode: only tools labeled read-only were run. How the test works

✕
Bad inputs give a clean error
3 failed, 5 warnings
- !validate_artifact: Accepted missing required input "artifact" without complaining
- ✕validate_artifact: Crashed on wrong type for "artifact"
- !validate_plan: Accepted missing required input "plan" without complaining
- !validate_plan: Accepted wrong type for "plan" without complaining
- !analyze_code: Accepted missing required input "code" without complaining
- ✕analyze_code: Crashed on wrong type for "code"
- !generate_code: Accepted missing required input "prompt" without complaining
- ✕generate_code: Crashed on wrong type for "prompt"
fail
!
Ready for the newest MCP version
1 warning
- !Uses an older MCP version (2024-11-05). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Fast enough
2 warnings
- !Average tool answer: 4.4 s
- !analyze_code: Slowest tool: analyze_code (7.9 s): users will notice the wait
- and 2 more
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !validate_ai_output: Labeled read-only, but it has a "ai_output" input described as "SQL statements". A read-only label can't promise much when the tool runs whatever it's sent; make the tool itself refuse changes (for example with a read-only database user), o
note
!
Resources and prompts work
5 warnings (6 resources, 5 prompts)
- !gate_my_changes: Doesn't complain when the required input code is missing.
- !review_my_plan: Doesn't complain when the required input plan is missing.
- !start_unit: Doesn't complain when the required input goal, task is missing.
- !triage_message: Doesn't complain when the required input message is missing.
- !record_progress: Doesn't complain when the required input unit_id is missing.
- and 3 more
note
✓
ConnectsConnected in 644 ms
pass
✓
Lists its toolsFound 5 tools
pass
✓
Every tool is describedAll 5 tools and their inputs are described
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 inputs
All good
- ✓validate_artifact: Worked (299 ms)
- ✓validate_plan: Worked (4.8 s)
- ✓analyze_code: Worked (7.9 s)
- ✓generate_code: Worked (4.5 s)
- –validate_ai_output: Not run: labeled read-only, but it has a "ai_output" input described as "SQL statements", so what it does depends on what it's sent. Skipped to be safe: if you own this server, test again with --owner
pass
✓
No secrets leakedChecked 3 error messages: no secrets or internal details
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

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://mcp.verificate.ai/mcp

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

[![QAmcp score](https://qamcp.dev/s/ai-verificate-mcp.svg)](https://qamcp.dev/s/ai-verificate-mcp.html)

Score over time

10 Nov 202670

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Verificate MCP, 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.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works