Provides measured design specs from real product screens for coding agents.
Do not connect
No critical issue was found, but the combined weight of the other findings put the score below 25/100. Remediate the findings before connecting this server.
Scanned 2 months ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The mozaika MCP server exposes 23 tools, focused primarily on AI capabilities. Its published description reads: "Provides measured design specs from real product screens for coding agents". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates mozaika F — no critical issue was found, but the combined weight of the other findings put the score below 25/100, so the findings should be remediated before connecting. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check mozaika's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add mozaika to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mozaika.design/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search real product UI screens for design reference. Use this BEFORE designing any page/component so your output matches how the best-designed products actually solve the problem. Returns structured m
List the distinct sections of a page (hero, pricing cards, testimonial/feedback, footer, ...) so you can emulate a specific part. Each section links back to its page (parent_slug) and the product's de
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: get_screen_sections
A tool description tries to alter the model’s use of another tool.
gn system (call get_design_system(site)).RecommendationDescriptions must describe only their own tool.
tool: list_user_flows
A tool description tries to alter the model’s use of another tool.
summaries; call get_user_flow(slug) for the full ordered screens.RecommendationDescriptions must describe only their own tool.
tool: get_design_system
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
pty for the raw token dict. Pass "all" to also get paste-ready DERecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_design_system
A tool description tries to alter the model’s use of another tool.
n systems (call list_my_design_systems) resolve first. format: leave empty for thRecommendationDescriptions must describe only their own tool.
tool: audit_code
A tool description tries to alter the model’s use of another tool.
instead of someone else's product. Give it the component's CSS,RecommendationDescriptions must describe only their own tool.
tool: get_web_benchmark
A tool description tries to alter the model’s use of another tool.
wn design, call validate_design(...). Free.RecommendationDescriptions must describe only their own tool.
tool: get_design_drift
A tool description tries to alter the model’s use of another tool.
ile. Pairs with get_design_system(site) — that gives the spec, this gives its sheRecommendationDescriptions must describe only their own tool.
tool: list_design_changes
A tool description tries to alter the model’s use of another tool.
oduct, call get_design_drift(domain). Args: limit: how many conRecommendationDescriptions must describe only their own tool.
tool: compare_components
A tool description tries to alter the model’s use of another tool.
tead of guessing. Args: component_type: e.g. "Button", "NavigRecommendationDescriptions must describe only their own tool.
tool: compare_recipes
A tool description tries to alter the model’s use of another tool.
instead of guessing at the invisible motion/state layer. This is the compaRecommendationDescriptions must describe only their own tool.
tool: get_product
A tool description tries to alter the model’s use of another tool.
t>" instead of many small calls. Your private BYODS systems resolve fiRecommendationDescriptions must describe only their own tool.
tool: list_my_design_systems
A tool description tries to alter the model’s use of another tool.
he slug/name to get_design_system or get_product to build against it. ReturnsRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ODUCT IS NAMED: get_design_system("Linear") for the whole system, or get_sectionRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
The tool surface changed after prior observation — the rug-pull signal. Flagged for review, not proof of malice.
RecommendationRe-review the server; pin trusted tool descriptions (TOFU).
tool: generate_asset
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "generate_asset"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
List real product user flows (ordered screen journeys) — e.g. signup→dashboard, browse→checkout. Use to understand how a whole journey is structured before building it. Returns flow summaries; call ge
Get one user flow with its ordered steps, each including full screen metadata and image_url. Returns an error dict if the flow is not found.
Get full metadata + image_url for a single screen by slug.
Get a product's full, LLM-verified design system so you can match its exact look. Use this for "design like <product>" (e.g. site="Linear", "Stripe", "Figma"). Returns (default): color_scheme; colors
Measured design CHANGE HISTORY for a live-decoded domain — the Decode Ledger. Token-level diffs between deep decodes over time: "radius 4px→8px", "primary hover #4032C8→#0A2540", "motion dominant 150m
When the user says a screen looks generic, cheap or off and you need to know WHY — paste the code and get numbers back. This is the one tool here that reads YOUR work instead of someone else's product
Grade YOUR design values against the measured corpus (hundreds of real products, decoded live — not opinions). Pass whichever metrics you have; each returns its percentile, the corpus median/p25/p75 a
The Measured Web — how the web is ACTUALLY designed, measured live across hundreds of real products (not opinions): the median design score, border-radius, body/hero font size, colour + light/dark spl
Has this product's design system CHANGED since it was decoded — and which of its numbers are safe to hard-code? Mozaika re-measures the most-referenced products from the live DOM every night and keeps
What actually changed in the web's design systems lately — the nightly Drift Ledger feed. Mozaika re-measures ~100 of the most-referenced products every night and records a dated row per product even
Get one product's specific section fully specified — its decoded spec + reference image_url + the parent product's design tokens — in a single call. Use this for "build a <section> like <product>", e.
See how the BEST products each solve the same section — one call, cross-product. Use before designing any section: e.g. compare_sections("Pricing / Plans") returns a ranked panel (one per product) of
Get one product's UI component fully specified — its anatomy read from the LIVE DOM (exact padding / height / border_radius / border / box_shadow / font_weight / letter_spacing / transition + the real
See how the BEST products each build the same UI atom — one call, cross-product, each with its anatomy read from the live DOM. Use before building any component: compare_components("Button") returns a
The universal BUILD-KIT fetcher — the measured spec + code to reproduce a piece of UI. `recipe_type` selects which library across three families (all agent-ready through this one call): • COMPONENTS (
See how the BEST products each build the same hard pattern — one call, cross-product. Use before building any complex pattern: compare_recipes("Command Palette") returns a ranked panel (one per produc
Pull an entire product as an agent-ready build kit: the full multi-format design system (tokens + DESIGN.md/Tailwind/CSS/JSON), every curated page, every section grouped by type (with spec + image_url
List YOUR private design systems (BYODS) — the sites you decoded into your own/your team's scope. Each item has name + slug; pass the slug/name to get_design_system or get_product to build against it.
Get a ready-made AI-generated icon pack (12 consistent icons) — e.g. a house style like 'clay-starter' / 'line-minimal-starter', or a pack generated in the MEASURED style of a decoded brand. Free and
Generate ON-BRAND icons with AI: subjects (1-12 short nouns, e.g. ["settings gear", "credit card"]) rendered in ONE consistent style. style_from is either a decoded domain ("stripe.com" — the icons ma
Design Score: a 0-100 design audit MEASURED from the site's live DOM (real WCAG contrast pairs, detected type ladder, spacing grid, forced hover states, motion) — scored against the whole measured-web