Loading…
Anti-slop design taste for AI coding agents: art directions, section code, and a 0-100 page critic.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month 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 standout MCP server exposes 30 tools, focused primarily on developer capabilities. Its published description reads: "Anti-slop design taste for AI coding agents: art directions, section code, and a 0-100 page critic". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates standout F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" 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 standout's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add standout to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://standoutmcp.io/api/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.
Get a complete, distinctive, reference-backed art direction for a website: palette with exact hex roles, type pairing, layout DNA, hero spec, component treatments, imagery rules, matched motion recipe
Browse the full 'pick a vibe' menu: all 14 named art directions (9 light-base, 5 dark-base) with their taglines, vibe tags, and what each is best for. Use when the user wants to SEE the available dire
Get a LOCKED design-token system for application UI (dashboards, admin panels, SaaS tools): every color role contrast-checked, exactly two radii, a five-step type scale, spacing, elevation and motion
Get FINISHED application-UI components (React + Tailwind, zero dependencies) written against a Standout app theme's semantic tokens: app shell with sidebar/topbar, stat row with mono tabular metrics,
Deterministic critique for APPLICATION UI (dashboards, admin panels, SaaS views): runs the app-UI slop rulebook against React/JSX/HTML source (radius chaos, card-in-card, gray-on-gray text, raw palett
Brutal, specific design critique of an existing page: automatic AI-slop detection (banned gradients, centered-hero defaults, h-screen bugs, cliche copy) plus a prioritized fix list with exact values.
THE PRIMARY STANDOUT WORKFLOW. Use this when a user wants an AI-built website made client-ready without choosing individual design tools. First call: pass url (best), source, or business. Standout cap
Detailed transformation plan for power users. For the complete inspect, fix, rerender, and client-proof workflow, prefer polish_and_prove. This tool classifies and scores a site, returns exact fix pat
Generate a CLIENT-READY design audit report for an agency to send to its client: a Standout Score, what's holding the page back, what to fix and why it matters, a client-safe summary, and the page scr
Finished, art-directed HTML/CSS page sections for a design direction: nav, hero, offer, image band, story, and footer — composed by a designer, seeded to this business (accent + expression already app
Get a complete hero section concept: headline + subline copy (no marketing cliches), CTA labels, exact background treatment, and copy-paste ambient motion CSS matched to the design direction.
Ready-to-paste CSS for a direction: custom properties (palette + fonts), button/card/nav treatments, grain texture, Google Fonts import, and the matched motion recipe list.
The tier ABOVE the design directions: finished showpiece skeletons for scene-led, art-directed pages - world hero with environment bleed, VIDEO world hero (looping cinematic clip + liquid-glass chrome
Production-ready motion for any stack: CSS/vanilla-JS recipes (staggered entrances, scroll reveals, marquees, grain, parallax) PLUS finished shader-grade ambient pieces - WebGL gradient mesh, image ri
Standout-original premium primitives: luxury hero backgrounds, Framer-style dials/gauges, shader/glass cards, soft section transitions, proof rails, pricing plates, and headline motion. Returns copy-p
Assemble a coherent premium build kit from Standout-original primitives: type scale, spacing rhythm, hero background, card/surface, dial or metric, section transition, text motion, and proof/pricing.
Search Standout's curated reference library: real public-product style, screen, and component patterns with source URLs, color roles, layout notes, component rules, do/don't constraints, and agent imp
Get the full structured payload for one reference: source URL, categories, tags, colors, typography, layout pattern, component rules, imagery, motion, do/don't constraints, and agent implementation no
Find references similar to a known reference by shared tags, categories, use cases, and StandOut direction ids. Use after finding one strong reference to broaden the evidence set.
Search reference-backed user journeys such as API key onboarding, pricing selection, hospitality booking, marketplace search, quickstart activation, and portfolio inquiry. Use when the page is part of
Get the full step-by-step payload for one user journey: problem, steps, user actions, system responses, related direction ids, and agent implementation notes.
Turn a business brief plus optional reference ids into a reference-backed build direction. Returns the chosen StandOut direction, matching public-product references, relevant flow patterns, a synthesi
Reference-first build — 'show me what you like, I'll build it.' Give a reference you LIKE (a public site URL via reference_url, and/or a curated library id via reference_id from search_references) plu
Reference Intelligence Layer — build from a site you like without cloning it. Pass a public reference_url plus what YOU are building and optional favorite_bits such as 'hero animation', 'pricing card'
Originality guardrail — compare a built page/source/description against a reference site and flag shared recognizable fingerprints. Use after build_from_reference_v2, before showing or publishing, to
Self-provision a free Standout trial key (25 calls, no signup) without leaving the conversation. Call this when no license key is configured or your Standout calls return a license error. Returns the
Unlock 10 bonus calls on this trial key, one time only, in exchange for the user's email address. Call this when the trial limit is reached and the USER has chosen the free-bonus option and given you
Watch a live site's design score (Pro). Standout re-audits the URL about once a day and emails an alert when the design regresses: a drop of more than 5 points, or falling below the 85 client-ready ba
Stop watching a site's design score. Pass the same URL that was given to watch_site. Unmetered.
List this license's active site watches with their last known scores and check times. Unmetered.
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_design_direction
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "current_site_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_design_direction
A tool description tries to alter the model’s use of another tool.
ad of defaults. The catalog holds 14 directions: 9 with light base paletteRecommendationDescriptions must describe only their own tool.
tool: get_design_direction
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
_url — Standout fetches it server-side and returns a content inventory (services, prices, hours, contacts) pRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: list_directions
A tool description tries to alter the model’s use of another tool.
ather than have get_design_direction auto-pick from the business. Pick an id from thRecommendationDescriptions must describe only their own tool.
tool: get_component_code
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
tic tokens: app shell with sidebar/topbar, stat row with mono tabularRecommendationAnnotate destructive tools and require human approval.
tool: get_component_code
A tool description tries to alter the model’s use of another tool.
tead of inventing structure. Install the theme first via get_app_theme.RecommendationDescriptions must describe only their own tool.
tool: critique_ui
A tool description tries to alter the model’s use of another tool.
nding PAGES use critique_design instead.RecommendationDescriptions must describe only their own tool.
tool: critique_design
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: critique_design
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: polish_and_prove
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: make_it_standout
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: make_it_standout
A tool description tries to alter the model’s use of another tool.
orkflow, prefer polish_and_prove. This tool classifies and scores a site, returnRecommendationDescriptions must describe only their own tool.
tool: client_report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_section_code
A tool description tries to alter the model’s use of another tool.
nstead of a template.RecommendationDescriptions must describe only their own tool.
tool: assemble_premium_page
A tool description tries to alter the model’s use of another tool.
d of generic advice.RecommendationDescriptions must describe only their own tool.
tool: synthesize_direction_from_references
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: build_from_reference
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "reference_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: build_from_reference
A tool description tries to alter the model’s use of another tool.
ad of a text brief: Standout reads the URL server-side for its semantic siRecommendationDescriptions must describe only their own tool.
tool: build_from_reference_v2
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "reference_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: critique_similarity
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "reference_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: critique_similarity
A tool description tries to alter the model’s use of another tool.
ints. Use after build_from_reference_v2, before showing or publishing, to avoid produciRecommendationDescriptions must describe only their own tool.
tool: watch_site
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: unwatch_site
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: unwatch_site
A tool description tries to alter the model’s use of another tool.
at was given to watch_site. Unmetered.RecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
tes. START with polish_and_prove whenever the user asks to build, redesign, restRecommendationDescriptions 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.
tool: client_report
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "client_report"RecommendationScope tools to the minimum needed.
tool: get_similar_references
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "get_similar_references"RecommendationScope tools to the minimum needed.
tool: watch_site
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "watch_site"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.