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 / ihumane

ihumane

Q: Is ihumane MCP server safe?

QAmcp's test on 10 Nov 2026: None of the hidden-instruction wordings we know were found in its 12 tool descriptions. Its error messages showed no secrets or internal details. 11 of its 12 tools are labeled read-only; the others may change or send things. Overall it scored 89/100 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 ihumane.ai · https://ihumane.ai/mcp

Human know-how for AI agents: rules, reasons and checks for design, code, product and writing.

12 tools✓ no account neededPricing: not listed

Visit website

89 /100

PASS · WITH NOTES

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: 12 tools
Its own safety labels: 11 read-only, 1 labeled as changing things
Memory it takes: About 3,300 tokens of your AI's memory, just for its tool descriptions
Largest answer: About 19.5 KB in our test
Speed: Average answer in our test: 57 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 our latest test, 10 Nov 2026.

Is ihumane MCP server safe?

None of the hidden-instruction wordings we know were found in its 12 tool descriptions.
Its error messages showed no secrets or internal details.
11 of its 12 tools are labeled read-only; the others may change or send things.
Overall it scored 89/100 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

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

12 tools, in the server's own words.

ihumane_startread-only

Call this at the START of any task you do for a person: a page, a feature, a bug fix, a new product idea, a database change, a document.

ihumane_ui_startread-only

Call this BEFORE designing or building any user interface (a page, screen, component or flow).

ihumane_code_startread-only

Call this BEFORE writing or changing code that people will keep (a feature, a fix, a refactor).

ihumane_product_startread-only

Call this BEFORE building a new product, feature or prototype, when what to build and for whom isn't settled.

ihumane_moduleread-only

Opens any ihumane module before that part of the work: its workflow, its first step and the rules likely to matter for your task.

ihumane_copy_startread-only

Call this BEFORE writing words people will read in a product: button labels, error messages, empty states, form labels and help, confirmations, notifications, …

ihumane_get_rulesread-only

Call this WHILE building, for the specific thing in front of you, e.g.

ihumane_translate_tasteread-only

Call this when your human describes the look, feel or voice with taste words ('clean', 'modern', 'premium', 'playful', 'make it pop', 'friendly', 'professional…

ihumane_reviewread-only

Call this BEFORE you tell your human the work is done.

ihumane_get_checkread-only

Returns a check to run on your own work.

ihumane_humanread-only

Call this once when you start working for a person, on any task (a site, a database, a domain, a document, not only UI).

ihumane_feedback

Call this once at the end of a task where you used ihumane, if something was missing, wrong or especially useful: a word with no entry, a rule that didn't fit …

Test results

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

!
Ready for the newest MCP version
1 warning
- !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 described
1 warning
- !ihumane_get_check: Description uses vague words ("something", "generic") instead of saying what it does and returns: "Returns a check to run on your own work. Browser checks run on the RENDERED page"
note
✓
ConnectsConnected in 1.4 s
pass
✓
Lists its toolsFound 12 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 inputs
All good
- ✓ihumane_start: Worked (69 ms)
- ✓ihumane_ui_start: Worked (54 ms)
- ✓ihumane_code_start: Worked (58 ms)
- ✓ihumane_product_start: Worked (54 ms)
- ✓ihumane_module: Worked (70 ms)
- ✓ihumane_copy_start: Worked (58 ms)
- ✓ihumane_get_rules: Worked (66 ms)
- ✓ihumane_translate_taste: Worked (53 ms)
- and 4 more
pass
✓
Bad inputs give a clean error
All good
- ✓ihumane_start: Refused wrong type for "task" with a clear error
- ✓ihumane_ui_start: Refused wrong type for "task" with a clear error
- ✓ihumane_code_start: Refused wrong type for "task" with a clear error
- ✓ihumane_product_start: Refused wrong type for "task" with a clear error
- ✓ihumane_module: Refused missing required input "name" with a clear error
- ✓ihumane_module: Refused wrong type for "name" with a clear error
- ✓ihumane_copy_start: Refused wrong type for "task" with a clear error
- ✓ihumane_get_rules: Refused missing required input "topic" with a clear error
- and 7 more
pass
✓
Fast enough
All good
- ✓Connecting took 1.4 s
- ✓Listing tools took 56 ms
- ✓Average tool answer: 57 ms
- ✓ihumane_module: Slowest tool: ihumane_module (70 ms)
pass
✓
No secrets leakedChecked 15 error messages: no secrets or internal details
pass
✓
Follows MCP best practices (not scored yet)Tool names, safety labels and tool list size follow the MCP guide
pass
✓
Resources and prompts work
All good (52 resources)
- ✓Opened 10 of 10 resources (a sample of 10 of 52)
- ✓An address that does not exist gets a clean "not found" error
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://ihumane.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-ihumane-ihumane.svg)](https://qamcp.dev/s/ai-ihumane-ihumane.html)

Score over time

10 Nov 202689

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use ihumane, 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