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
Directory / Designers
Designers
by designers.allthepossibles.com · https://designers.allthepossibles.com/mcp
Checks, prompts and skills for designers working with AI: contrast, a11y, heuristics, critique.
12 of 12 checks · 30 Oct 2026
Is Designers MCP server safe?
- No hidden instructions were found in its tool descriptions.
- Its error messages showed no secrets or internal details.
- All 60 of its tools are labeled read-only.
- Overall it scored 73/100 on 30 Oct 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 it can do
60 tools, in the server's own words.
check_contrastread-onlyCheck color contrast.
audit_page_accessibilityread-onlyAudit one page's static HTML for accessibility problems and name the WCAG 2.2 criterion for each: missing lang or title, images without alt, unlabeled form fie…
heuristic_worksheetread-onlyBuild a Nielsen ten-heuristics review worksheet for a screen or flow.
detect_design_slopread-onlyLook for the default AI-generated design look in a live page's markup and CSS: purple-to-blue gradients, gradient text, a default font stack, pill buttons with…
review_ui_copyread-onlyReview interface copy, one string per line, optionally prefixed with a type (button:, error:, empty:, tooltip:, placeholder:, heading:, toast:, label:).
lint_design_feedbackread-onlyLint design critique.
plan_critiqueread-onlyPlan a design critique for a stage (concept, wireframe, visual, prototype, build, shipped): a framing statement, timed agenda, the questions that fit the stage…
lint_research_questionsread-onlyLint user research questions, one per line, for leading wording, double-barrelled questions, hypotheticals, predictions, loaded words, jargon, closed questions…
usability_statsread-onlyUsability arithmetic with formulas shown.
lint_tracking_planread-onlyLint a product analytics tracking plan (event names with optional properties, one per line like 'project_created (template, source)') for mixed naming styles, …
audit_site_accessibilityread-onlyPro.
check_contrast_tokensread-onlyTake a design token file (CSS custom properties like --color-text: #111;, a JSON object of colors, or W3C design tokens) and test every foreground-like token a…
build_heuristic_reportread-onlyPro.
getting_startedread-onlyExplain what this server can do and suggest the three best first tasks for what the person has (a Figma link, a live URL, copy, a research plan, an event list).
whoamiread-onlyShow the caller's plan (Free or Pro) and how many calls remain today on each tool.
check_touch_targetsread-onlyCheck target sizes and spacing against WCAG 2.2 SC 2.5.8 (24 by 24 CSS px, or a smaller target with enough spacing), the 44px guidance for iOS and the web, and…
lint_token_namesread-onlyLint design token names from a list, CSS variables or a JSON token file: mixed separators, colors named by hue where roles belong, values or locations in names…
lint_design_mdread-onlyScore a DESIGN.md (the brand and design context file models read before building): missing sections, no hex values, text and background pairs that fail contras…
doctorread-onlyDiagnose setup problems.
save_project_contextread-onlyPro.
get_project_contextread-onlyPro.
generate_conformance_reportread-onlyPro.
screen_reader_scriptread-onlyRead HTML (pass `html`, or a public `url`) and return a linear approximation of what a screen reader announces, in document order: landmarks, headings with lev…
check_motionread-onlyStatic motion audit against WCAG 2.2 (2.2.2 Pause, Stop, Hide; 2.3.1 Three Flashes; 2.3.3 Animation from Interactions).
and 36 more
Test results
Safe mode: only tools labeled read-only were run. How the test works
- ✕Resources and prompts workfail
1 failed, 1 warning (15 resources, 23 prompts)
- ✕designers://playbooks/ecommerce-checkout: Listed, but opening it is refused: Playbook: e-commerce checkout (Pro) is part of Pro ($5/mo, 7-day free trial). Start it at https://designers.allthepossibles.com/#pro and ad…
- !Opened 9 of 10 resources (a sample of 10 of 15)
- and 2 more
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
4 warnings
- !plan_usability_test: Inputs with no description: product, method
- !data_table_vs_chart: Inputs with no description: rows, cols, purpose, precision, space, timeSeries, mixedUnits, groups, audience
- !number_format_check: Inputs with no description: context
- !plan_responsive_images: Inputs with no description: format, aboveFold, maxViewport, content
- !Bad inputs give a clean errornote
10 warnings
- !detect_design_slop: Accepted missing required input "url" without complaining
- !lint_design_feedback: Accepted missing required input "text" without complaining
- !plan_critique: Accepted missing required input "description" without complaining
- !lint_research_questions: Accepted missing required input "text" without complaining
- !check_contrast_tokens: Accepted missing required input "tokens" without complaining
- !getting_started: Accepted wrong type for "have" without complaining
- !lint_token_names: Accepted missing required input "text" without complaining
- !lint_design_md: Accepted missing required input "text" without complaining
- and 32 more
- !Fast enoughnote
1 warning
- !whoami: Slowest tool: whoami (2.6 s): users will notice the wait
- and 3 more
- !Follows MCP best practices (not scored yet)note
2 tips (not scored)
- !The tool list is about 176 KB (roughly 44k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
- !error_state_writer_template: Labeled read-only, but its "where" input is a filter with no pattern, length limit or fixed choices. Make sure it can't reach outside what it's meant for (like a filter that matches everything), and add a pattern so AI apps know what fits.
- ✓ConnectsConnected in 270 mspass
- ✓Lists its toolsFound 141 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No hidden instructionsNo hidden instructions found in tool descriptionspass
- ✓Tools work with good inputspass
All good
- ✓check_contrast: Worked (542 ms)
- ✓audit_page_accessibility: Worked (199 ms)
- ✓heuristic_worksheet: Worked (191 ms)
- ✓detect_design_slop: Worked (202 ms)
- ✓review_ui_copy: Worked (196 ms)
- ✓lint_design_feedback: Worked (1.1 s)
- ✓plan_critique: Worked (191 ms)
- ✓lint_research_questions: Worked (202 ms)
- and 32 more
- ✓No secrets leakedChecked 135 error messages: no secrets or internal detailspass
- –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://designers.allthepossibles.com/mcpShow 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.
[](https://qamcp.dev/s/com-allthepossibles-designers.html)Score over time
- 30 Oct 202673
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use Designers, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works