DS4AI MCP
This server lets an AI agent audit and generate web deliverables across findability, delivery, and accessibility/contrast using DS4AI primitives.
Audit shipped web surfaces:
audit_surfacechecks a live URL or raw HTML across six invisible-correctness axes, declaring axes that static checks cannot judge.Generate findability assets:
generate_head,generate_jsonld,generate_sitemap,generate_robotscreate head tags, JSON-LD, sitemaps, and robots.txt.Audit findability:
audit_findabilityreviews a page's HTML for head essentials, Open Graph, Twitter, JSON-LD validity, and canonical/og:url agreement.Generate delivery assets:
generate_image_markupandgenerate_cache_configproduce responsive image/picture markup and host-specific cache-header configs.Audit delivery:
audit_deliverychecks HTML for unsized images, lazy-loaded first images, render-blocking scripts, and font-display issues.Solve and check palettes:
solve_palettebuilds contrast-verified semantic tokens for a mode/notch/family/vision, andcheck_contrastcomputes WCAG 2.1 contrast ratios against AA thresholds.Expose resources: the server provides
ds4ai://manifest,ds4ai://agents, andds4ai://standardresources for agent guidance and standards reference.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DS4AI MCP Audit https://example.com for conformance and suggest improvements."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DS4AI MCP server
The aggregate endpoint of DS4AI, the Design Suite for AI, from Polymathie-Studio. It serves the suite as callable MCP tools, so a person working with an AI reaches the conformance auditor and the generators through their agent, without calling a function. Unlike the @proof-of-coord standards servers, which point at canonical source, this server runs the primitives, and because it is a process rather than a browser it can fetch a URL and audit the served HTML.
Use it
This server is hosted as a public HTTP endpoint, and is published to npm and JSR as @polymathie/ds4ai. Connect the hosted server with nothing to install:
{
"mcpServers": {
"ds4ai": { "type": "http", "url": "https://ds4ai-production.up.railway.app/mcp" }
}
}Or run it locally, no clone:
npx @polymathie/ds4ai # from npm
deno run -A jsr:@polymathie/ds4ai # from JSR (Deno)Add it to an MCP client (Claude Code, Cursor, and the rest) either as the hosted HTTP server above, or as a stdio server whose command is npx @polymathie/ds4ai. The four MCP servers are listed at integritysuite.org/built, and the full reference for every connection method is Using the MCP servers.
Related MCP server: aeo-graph-engine
Tools
audit_surface
{ url? , html? }: audit a shipped surface across all six invisible-correctness axes with the MISSING conformance auditor. Give a URL and it fetches and audits the served HTML. Declares the axes a static check cannot judge rather than reporting them clean.generate_head, generate_jsonld, generate_sitemap, generate_robots, audit_findability (BEACON): findability head tags, JSON-LD, sitemap, robots.txt, and the depth findability audit.
generate_image_markup, generate_cache_config, audit_delivery (FLEET): responsive image and picture markup, cache-header config per host, and the depth delivery audit.
solve_palette, check_contrast (TEMPER): solve a full palette to contrast floors for a mode, and check the WCAG contrast between two colors.
Every result carries a provenance stamp declaring the server and bundled primitive versions.
Resources
ds4ai://manifest: the DS4AI family manifest (read generically, so it tracks the manifest as its data source).ds4ai://agents: the agent-instruction (AGENTS.md), so a connected agent gets the compose-the-suite instruction for free.ds4ai://standard: the MISSING standard.
How it is built
TypeScript on the MCP SDK with zod schemas, provenance-stamped, following the @proof-of-coord pattern. The zero-dependency primitives (TEMPER, BEACON, FLEET, and the MISSING conformance auditor) are bundled in, so the server is self-contained, and each tool stamps the primitive version it bundled. Published to npm and JSR under @polymathie.
Security
The URL-auditing path (audit_surface fetching a live URL) is built to a defensive threat model and is adversarially tested and hardened before release against server-side request forgery, denial-of-service, and resource-exhaustion attacks. Fetched content is treated as untrusted input: it is parsed, never executed, and the fetcher connects only to validated public addresses. The implementation is open for review under Apache-2.0.
Part of DS4AI
DS4AI, the Design Suite for AI, from Polymathie-Studio, joins PT4AI and PC4AI in the family of corpora served to an AI. The instruments and the MISSING standard live at Polymathie-Studio.
License
Apache-2.0 for the server. Copyright 2026 Regis Lloyd Chapman. See LICENSE and NOTICE.
The bundled resources keep their own licenses, from the Polymathie-Studio/missing repository: resources/standard.md (the MISSING standard) is dual-licensed CC-BY-4.0; the manifest and AGENTS.md are Apache-2.0. The vendored primitive source under src/vendor/ is Apache-2.0, from its instrument repository.
Available Tools
11 toolsaudit_deliveryB
Audit a page HTML string for delivery in depth (FLEET): unsized images, a lazy-loaded first image, render-blocking head scripts, and inline @font-face without font-display.
Inputs: html (required).
audit_findabilityA
Audit a page HTML string for findability in depth (BEACON): head essentials, Open Graph, Twitter, JSON-LD validity, and the canonical-versus-og:url agreement invariant.
Inputs: html (required).
audit_surfaceA
Audit a shipped web surface across all six invisible-correctness axes (perceivable, operable, off-happy-path, key-private, findable, fast-and-stable) with the MISSING conformance auditor. Pass a url to fetch and audit the served HTML, or pass html directly. Returns a per-axis report that declares the axes a static check cannot judge rather than reporting them clean.
Inputs: url, html.
check_contrastA
Check the WCAG 2.1 contrast ratio between two hex colors and whether it clears the AA thresholds (4.5:1 for normal text, 3:1 for large text or non-text).
Inputs: background (required), foreground (required).
generate_cache_configA
Generate cache-header config for a named host (netlify, vercel, nginx): revalidate HTML, cache content-hashed assets for a year as immutable.
Inputs: target (required), options.
generate_headA
Generate the findability head tags (title, description, canonical, Open Graph, Twitter card) for a page from a flat metadata object, as an SSR/build-time string. Also returns the html lang attribute.
Inputs: metadata (required).
generate_image_markupA
Generate responsive or markup with reserved dimensions and correct scheduling. Mark the LCP image priority (eager, high fetchpriority); mark offscreen images lazy. Pass avif/webp for format negotiation to get a .
Inputs: image (required).
generate_jsonldA
Serialize one or several schema.org objects into a JSON-LD script tag, with the sequence escaped. Pass a schema object or an array of them.
Inputs: schema (required).
generate_robotsA
Serialize a robots.txt for crawl control. Pass allow/disallow (string or array) and one or more sitemap URLs. Index control belongs in the head robots directive, not here.
Inputs: options (required).
generate_sitemapA
Serialize a sitemap.xml from a list of canonical URLs (strings, or objects with loc, lastmod, changefreq, priority).
Inputs: urls (required).
solve_paletteA
Solve a full TEMPER palette to verified contrast floors for a mode. mode is light, soft-light, soft-dark, or dark; notch is 0 (brighter), 1 (middle), or 2 (deeper); family is a color family key (for example iron, oxblood, moss); vision constrains for a color-vision deficiency (default, rg, by, mono). Returns the semantic token set.
Inputs: mode (required), notch, family, vision.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool names a distinct artifact or audit focus (head, JSON-LD, sitemap, robots, images, cache, palette, contrast). The only mild overlap is audit_surface versus audit_findability/audit_delivery, but the descriptions clearly differentiate a broad holistic audit from in-depth single-axis audits.
Tool names consistently follow a verb_noun pattern: generate_* for output serializers, audit_* for auditors, plus solve_palette and check_contrast. There is no mixed casing or vague verb style, making the naming pattern predictable and readable.
11 tools is well within the ideal scope for a web-correctness toolkit. Each generator and auditor addresses a distinct deliverable or audit pass, and none feels redundant or out of place.
The set covers core generation (head, structured data, sitemap, robots, images, cache) and auditing (surface, findability, delivery) plus color accessibility. The main gap is that index/noindex control is mentioned as living in the head, but no tool directly emits that meta robots directive.
Maintenance
Related MCP Connectors
Autonomous AI agent readiness, crawler reachability, and 30-point audit specification engine.
Robots-aware website audits, pre-crawl quotes, and structured evidence for people and agents.
Website health, SEO, security-header, SSL and broken-link audits for AI agents.
Live AEO, GEO, JSON-LD Schema, robots.txt AI crawler, and Agent Readiness diagnostic auditor.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to check whether a public website is crawlable, understandable, and ready for AI search workflows through local-only audits of robots.txt, sitemaps, metadata, and llms.txt.373 npm2MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to crawl live websites, audit AEO readiness, generate Schema.org @graph JSON-LD, llms.txt, ai.txt, and robots.txt, inject structured data into HTML, validate optimizations, and retrieve framework-specific code snippets.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to scan pages and whole sites for SEO and AI-search visibility, generate ready-to-paste fixes and validated structured data, and verify HTML before deploy and live results after — all through stable issue codes so an agent can fix problems one by one and prove they are gone.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to audit a web page in one call — title, meta description, canonical, robots, Open Graph, headings, JSON-LD, security headers and page delivery — returning each finding with its evidence and a ready patch to apply. It also compares a deploy preview against production to surface only regressions, keeps audited pages in tabs with history and daily watches, and runs Lighthouse lab tests via PageSpeed Insights.1MIT No Attribution