Designers

141 tools for design, accessibility, UX, typography, colour and site audits. Free tier, with Pro for unlimited use.

View on allthepossibles.com

Hosted MCP Server

npx add-mcp 'https://designers.allthepossibles.com/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

The parts of design your AI gets wrong, done properly.

Contrast maths, accessibility audits, critique and heuristic methods, research plans, copy review, handoff. Connect it to your AI assistant with one web address and it does these properly instead of guessing. See what each tool does with a real example first. New to this? Start here, or see how to connect Claude, Cursor, VS Code, Codex or ChatGPT.

Seven to try first

Each card shows the exact input and the real output from running it. The other 134 work the same way.

  • Contrast

    Find which text and UI colour pairs fail WCAG contrast and get the nearest colour that passes. You get: Per pair: WCAG ratio, pass or fail, APCA Lc, a passing colour; plus palette merges for colour-blind users Saves about 10 min (our estimate vs checking each pair in a contrast app and hunting for a passing shade by hand) Before 
    fg: #8a8a8a
bg: #ffffff
sizePx: 16
palette: #d62828 #2a9d3f #1d70b8 #f4b400
    After 
    #8a8a8a on #ffffff  3.45:1  AA FAIL  (normal text)  APCA Lc 62.1
   APCA: enough for 24px regular or 16px bold; too low for body…
   nearest passing: #767676 (4.54:1)
Palette (contrast of each colour on white and on black):
  #d62828  5.01:1 on white, 4.19:1 on black
  #2a9d3f  3.5:1 on white, 5.99:1 on black

  • Page accessibility

    Scan one page's HTML for accessibility problems and see the WCAG criterion behind each one. You get: Issues ranked high, medium and low, each with its WCAG criterion and an example element Before 
    https://allthepossibles.com
    After 
    "All the Possibles: tools that check themselves before they shi…
0 high, 0 medium, 0 low
No static findings.
Static HTML only. It does not render the page, so it cannot tes…

  • Touch targets

    Check button and control sizes against WCAG 2.5.8, iOS and web 44, and Android 48 targets. You get: A pass or fail per target for the 24px rule, the 44 and 48 sizes, and a note on how to fix each Saves about 5 min (our estimate vs measuring each control and comparing it with the guidelines by hand) Before 
    Close icon 32x32 gap=4
Save button 40x32 gap=8
Tiny toggle 16x16
Inline link 14x14 inline
    After 
    4 targets: 1 fail WCAG 2.5.8 (24 by 24 minimum), 4 under 44, 4 …
ok    Close icon  32x32 gap 4  2.5.8 pass, 44: no, 48: no
      Meets WCAG 2.2 AA but is small for fingers; use 44 on iOS…
ok    Save button  40x32 gap 8  2.5.8 pass, 44: no, 48: no
      Meets WCAG 2.2 AA but is small for fingers; use 44 on iOS…
FAIL  Tiny toggle  16x16  2.5.8 fail, 44: no, 48: no

  • Conformance report

    Draft a VPAT-style WCAG 2.2 conformance report from an automated audit of up to 10 pages. You get: A markdown report with a row for each of 55 A and AA criteria, from Supports to Not Evaluated Saves about 1.5 h (our estimate vs writing the 55-row VPAT table by hand, row by row, before any manual testing) Before 
    urls: ["https://allthepossibles.com","https://designers.all…
productName: All the Possibles site
version: 2026-10
vendor: All the Possibles
    After 
    # Accessibility Conformance Report (DRAFT)
WCAG 2.2 Edition, laid out after the ITI VPAT 2.5 template
> **Draft from automated checks. This is not a legal conformanc…
## Report header
| Field | Value |
| --- | --- |

  • AI design slop

    Spot the common AI design defaults in a page's markup and CSS, such as eyebrow labels and arrow buttons. You get: A slop-signal score out of 100 and each signal found, with an example from the code Before 
    https://allthepossibles.com
    After 
    few signals (0/100) in allthepossibles.com; read 20,554 bytes o…
  No signals found in the markup and styles that were read.
These are signals, not proof: a deliberate design can use any s…

  • UI copy

    Review buttons, errors, empty states and tooltips for what each must do, and flag AI-writing tells. You get: A list of strings with high, medium and low notes on each, plus consistency problems across the set Before 
    button: Submit
error: Invalid input
error: Oops! Something went wrong.
empty: No projects
    After 
    6 strings: 3 high, 5 medium, 1 low
[button] Submit
   MEDIUM "Submit" does not say what happens; name the outcome …
[error] Invalid input
   HIGH   says what went wrong but not what to do about it
   MEDIUM "invalid" names no field and no rule; say which and w…

  • Usability numbers

    Score SUS results and work out sample sizes for usability tests, A/B tests and surveys. You get: SUS score with grade, percentile and 95% interval, or the sample size needed, with the formula Before 
    mode: sus
responses:
  4 2 4 1 5 2 4 2 4 2
  3 3 4 2 4 3 3 2 4 3
    After 
    SUS 79.2 from 3 participants, 95% interval 38.8 to 100 (sd 16.3)
Grade B on the Sauro and Lewis curve; the adjective scale calls…
Per participant: 80, 62.5, 95
With 3 participants the interval is wide; treat the score as a …
Scoring: odd items score answer minus 1, even items score 5 min…

Browse all 141 tools

Search by the problem you have, or filter by who it is for and what you give it.

Free

Every check, every method and every reference guide, right here or in your AI assistant, with a daily cap per tool (10 to 60 runs on the busiest ones; each tool page lists its own). Enough to check a palette, audit a page, or sort a pile of critique notes. Exactly what each plan includes. Want the finished document instead? The Accessibility Readiness Report is $149 once, for one site.

Pro $5/mo

  • No daily caps on any tool, 300 requests a minute.
  • A site-wide accessibility crawl, scored heuristic reports, bigger token matrices.
  • Saved project context and the industry playbooks (checkout, onboarding, forms, dashboards, mobile).
  • Text tools take 200,000 characters instead of 20,000.
  • One API key that works on every route and on /mcp.