Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ihumane

REMOTE · IHUMANE.AI

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

Available components

+3 this week 74 Trust /100

Last scanned (19 hours ago)

Scores higher than 60% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability49
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 3532 tokens (~55/item across 64 items; 12 tools + 52 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 10 Nov 26 69

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://ihumane.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=ihumane.ai CN=YR1,O=Let's Encrypt,C=US 6 Nov 2026 4 Feb 2027 RSA 2048 SHA256-RSA 66cac06d61af4087a10da946b1be5d07bd5
SANs: ihumane.ai
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of ihumane.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
ihumane.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://ihumane.ai/mcp Verified 200
http (plaintext) http://ihumane.ai/mcp HTTPS enforced 308 https://ihumane.ai/mcp
MCP tools · 12 exposed · ~2,329 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ihumane_code_start ~151

Call this BEFORE writing or changing code that people will keep (a feature, a fix, a refactor). Returns the Code craft workflow: how to size the job, what to read before writing (existing helpers, the file's conventions, where the ask ends, how it's run and tested), and the rules likely to matter for your task. Ends with the tidy check to run on your change. Free: the workflow, the first step and the core rules; the other rules are ihumane Pro and are named by title.

NameTypeReqDescription
taskstring–What you're about to change, e.g. 'add retry to the payment webhook handler' or 'fix the date bug in reports'

No output schema declared.

No examples provided.

ihumane_copy_start ~122

Call this BEFORE writing words people will read in a product: button labels, error messages, empty states, form labels and help, confirmations, notifications, emails, onboarding, page copy. With ihumane Pro: the full Copy and UX writing workflow, the voice rules, and the rules most likely to matter for your task. Without Pro: the module overview and its seven most important rules.

NameTypeReqDescription
taskstring–What you're about to write, e.g. 'error messages for a payment form' or 'empty states for a project list'

No output schema declared.

No examples provided.

ihumane_feedback ~184

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 the task, a check that caught a real bug, advice that was too heavy for a small job. People who write ihumane's rules read every message. Write in general terms: no names, emails, URLs, code or anything private about your human or their project.

NameTypeReqDescription
helpedstring–What helped, and why. E.g. 'The stability check caught a button that resized while loading.'
missingstring–What was missing, wrong or didn't fit. E.g. 'No entry for the taste word exciting.'
taskstring–The kind of task, in general terms. E.g. 'landing page for a small food brand'

No output schema declared.

No examples provided.

ihumane_get_check ~538

Returns a check to run on your own work. Browser checks run on the RENDERED page (browser console or a browser tool's evaluate/execute): 'spacing': text touching lines, uneven padding. 'contrast': text and field edges too faint against their real background, in light and dark mode. 'affordance' (Pro): controls that look like something they aren't, link underlines, back-link direction. 'stability' (Pro): controls that move or resize when used. 'copy' (Pro): vague labels, 'click here' links, placeholder-only fields, missing alt text, errors with no next step, machine-voice words. Code check, run with Node in the project: 'tidy': leftovers in your change (debug logs, .only in tests, empty catches, likely secrets, new TODOs, commented-out code, very long functions). 'wayfinding' (UX design): Pages that don't say where you are or give a way back: no clear heading or a generic page title, menus with no current item, a breadcrumb that links to itself, a deep page with no way up, a step with no Back or way out, and dead ends. 'images' (Graphics and images): Images shown larger than the file (blurry), files far wider than their slot, stretched images, broken images, images with no width and height, missing or useless alt text, icon-only buttons with no name, heavy files, and icons in one row with different sizes, strokes or styles. 'diffmap' (Code review): The shape of a change before you review it: size, a reading order, and what to look at closely (code changed with no test, migrations, data deletes, risky paths, removed exports still in use, new dependencies, imports of packages the project doesn't have, tests that mock what they test). 'layout' (Front-end build): Sideways scrolling and the element causing it, text cut off by a fixed height, tap targets that are too small at touch widths, stretched or oversized images, clickable divs with no role, fields with no label or the wrong type, and skipped heading levels. 'trust' (QA and testing): Tests you can't trust: tests th…

NameTypeReqDescription
namestringyesWhich check to get

No output schema declared.

No examples provided.

ihumane_get_rules ~190

Call this WHILE building, for the specific thing in front of you, e.g. 'loading button', 'card header spacing', 'success message', 'pricing page', 'empty state', 'contrast', 'error message wording', 'error handling', 'naming', 'tests', 'who is it for', 'unasked features', 'asking my human a question', 'reporting a failed step'. Covers UI design, Code craft, Product thinking and Working with your human (and Copy with Pro). Returns the matching rules in full: the rule, why it matters to a person, the agent trap, and how to check it. Without Pro: the matching free rules in full, and the titles of matching Pro rules.

NameTypeReqDescription
limitinteger–How many rules to return (default 4)
topicstringyesWhat you're working on, in plain words

No output schema declared.

No examples provided.

ihumane_human ~137

Call this once when you start working for a person, on any task (a site, a database, a domain, a document, not only UI). Returns how to read what they mean (fast or dictated messages, odd words), when and how to ask, how to hand them a step they must do themselves (sign-ins, clicks, payments) so they can find it, and how to report. Pass a situation to get the most relevant rules first.

NameTypeReqDescription
situationstring–Optional: what's happening, e.g. 'my human must approve a sign-in link' or 'reporting a step that failed'

No output schema declared.

No examples provided.

ihumane_module ~219

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_start tells you which modules apply. Modules: ihumane core: 'humans' (Working with your human). Design: 'ui-design' (UI design), 'ux-design' (UX design), 'graphics' (Graphics and images). Engineering: 'code-craft' (Code craft), 'front-end' (Front-end build), 'code-review' (Code review), 'qa-testing' (QA and testing). Product: 'product-thinking' (Product thinking). Writing: 'copy' (Copy and UX writing). Free: each module's start; the other rules are ihumane Pro and are named by title.

NameTypeReqDescription
namestringyesThe module, e.g. 'qa-testing' or 'ux-design'
taskstring–What you're about to do, in a sentence, e.g. 'test the new checkout before release'

No output schema declared.

No examples provided.

ihumane_product_start ~141

Call this BEFORE building a new product, feature or prototype, when what to build and for whom isn't settled. Returns the Product thinking workflow: who it's for (one person in one situation, never invented), the problem behind the request, what success looks like, and what not to build. Small changes to an existing product get a two-line check instead. Free: the workflow, the first step and the core rules; the other rules are ihumane Pro and are named by title.

NameTypeReqDescription
taskstring–What you've been asked to build, e.g. 'a habit tracker app' or 'add team sharing to the notes app'

No output schema declared.

No examples provided.

ihumane_review ~226

Call this BEFORE you tell your human the work is done. Pass the kind of work. Each module's own review: 'ux', 'graphics', 'front-end', 'code-review', 'qa'. 'ui': render it and look at it, six review lenses (free: the user and accessibility lenses; Pro adds designer, writer, product manager and engineer), and the browser checks. 'code': run it, the verify rules and the tidy check. 'product': walk it through as the person it's for. 'writing': the copy review (Pro). 'other' (any other task): check it against what they asked, then the report rules. Every kind ends with how to report honestly.

NameTypeReqDescription
kindstring–The kind of work you're about to call done. A page with new code: 'ui' (it covers the screen; also run the tidy check). A flow across screens: 'ux'. Images: 'graphics'. Front-end code: 'front-end'. R…

No output schema declared.

No examples provided.

ihumane_start ~134

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. Returns which ihumane modules apply and the start tool to call next (UI design, Code craft, Product thinking, Copy), the five rules for working with a person on any task, and the rules most likely to matter for this task.

NameTypeReqDescription
taskstring–What you've been asked to do, in a sentence, e.g. 'fix the date bug in reports' or 'a pricing page for a small SaaS'

No output schema declared.

No examples provided.

ihumane_translate_taste ~136

Call this when your human describes the look, feel or voice with taste words ('clean', 'modern', 'premium', 'playful', 'make it pop', 'friendly', 'professional', 'sounds robotic') or feeling words ('exciting', 'amazing', 'wow', 'make people excited'). Returns the concrete decisions those words usually mean. Say your translation back to the human in one line BEFORE building or writing, so a wrong reading costs nothing.

NameTypeReqDescription
wordsstringyesThe human's words, as they wrote them, e.g. 'clean and modern' or 'make it more friendly'

No output schema declared.

No examples provided.

ihumane_ui_start ~151

Call this BEFORE designing or building any user interface (a page, screen, component or flow). Returns the ihumane workflow and the brief: what to find out first, which questions to ask your human (at most 3, each with a default), and which pattern choices you must not make silently. If you pass the task, it also lists the rules most likely to matter. Free: the workflow, the first step and the core rules; the other rules are ihumane Pro and are named by title.

NameTypeReqDescription
taskstring–What you're about to design or build, in a sentence, e.g. 'settings page for a small-team task app, clean and modern'

No output schema declared.

No examples provided.

Install

How do I install the ihumane MCP server?

ihumane is a hosted endpoint at https://ihumane.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · ihumane.ai

# add to Claude Code
claude mcp add --transport http ai-ihumane-ihumane 'https://ihumane.ai/mcp'
Common questions

What is the ihumane MCP server?

ihumane is an MCP server listed in the public MCP registry as ai.ihumane/ihumane. Human know-how for AI agents: rules, reasons and checks for design, code, product and writing. This page covers its hosted endpoint (https://ihumane.ai/mcp).

Is the ihumane MCP server safe to use?

ihumane scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the ihumane MCP server expose?

ihumane exposes 12 tools: ihumane_start, ihumane_ui_start, ihumane_code_start, ihumane_product_start, ihumane_module, and 7 more. Their descriptions and schemas cost roughly 2,329 tokens of context every time the server is loaded.

Does the ihumane MCP server require authentication?

No. We connected to ihumane without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the ihumane MCP server still maintained?

ihumane is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the ihumane MCP server?

VerifyMCP ran 13 checks on ihumane, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.