# Standout (remote · standoutmcp.io) Anti-slop design taste for AI coding agents: art directions, section code, 0-100 page critic. - Trust score: 67/100 (medium) - Change this week: +6 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-03 ## Components - remote · `standoutmcp.io`: 67/100 (this document), [markdown](https://verifymcp.io/servers/io-standoutmcp-standout/api-mcp.md), [page](https://verifymcp.io/servers/io-standoutmcp-standout/api-mcp) ## Channel facts - Endpoint: `https://standoutmcp.io/api/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.0.2` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-08-03. - **Endpoint Security**: 66/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation not fully verified: no authorisation is required to call this server, and 30 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC is configured correctly; the domain's records validate against the full chain to the root. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 57/100 - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 5705 tokens (~190/item across 30 items; 30 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 27/100 - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### Claude ```bash claude mcp add --transport http io-standoutmcp-standout https://standoutmcp.io/api/mcp ``` ### Codex ```toml [mcp_servers.io-standoutmcp-standout] url = "https://standoutmcp.io/api/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "io-standoutmcp-standout": { "type": "remote", "url": "https://standoutmcp.io/api/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add io-standoutmcp-standout --url https://standoutmcp.io/api/mcp --transport streamable-http ``` ### Hermes ```yaml mcp_servers: io-standoutmcp-standout: url: "https://standoutmcp.io/api/mcp" ``` ### Other ```json { "mcpServers": { "io-standoutmcp-standout": { "type": "http", "url": "https://standoutmcp.io/api/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-08-03 (score 67, +1) No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-08-01 (score 66, +1) No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-07-31 (score 65, +2) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-30 (score 63, 0) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-29 (score 63, +1) No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-07-28 (score 62, +1) No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-07-27 (score 61, 0) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-26 (score 61) First indexed and scored. ## MCP tools (30) ### `get_design_direction` (~448 tokens) 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 recipes, and public-product reference evidence. Use FIRST, before building, so the site has a coherent direction instead of defaults. The catalog holds 14 directions: 9 with light base palettes and 5 dark — pass tone to constrain. If you only know the business name, call it anyway: the response will give you a few quick questions to ask the user, then call again with their answers as vibe/audience. REDESIGNS: if the business has an existing website, pass its URL as current_site_url — Standout fetches it server-side and returns a content inventory (services, prices, hours, contacts) plus a redesign protocol, so no questions are needed. Input parameters: - `audience` (string): Who the site must convince - `boldness` (string): How adventurous the signature concept should be: safe (conservative/trust-first businesses like clinics, accountants, law firms), elevated (default), bold, or experimental. A 'safe' request never rec… - `business` (string): What the business is, e.g. 'dive shop in Fiji running charters'. If omitted, the response returns a few quick intake questions to ask the user instead of erroring. - `current_site_url` (string): The business's EXISTING website URL, for redesigns. Standout fetches it and returns the content to preserve + the redesign protocol - `industry` (string): Industry, e.g. restaurant, law firm, saas, gym - `tone` (string): Base palette tone. Pass when the client asks for a light or dark site; matching stays inside that pool (9 light / 5 dark directions) - `vibe` (string): Desired feel, e.g. premium, playful, technical, warm ### `list_directions` (~175 tokens) 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 directions and choose one themselves, rather than have get_design_direction auto-pick from the business. Pick an id from the menu and pass it as the `direction` argument to get_section_code, get_asset_pack, get_hero_concept, or synthesize_direction_from_references. Browsing the menu does not consume a metered call. Input parameters: - `response_format` (string): Return a human-skimmable markdown menu (default) or a structured JSON array - `tone` (string): Optionally show only light-base (9) or dark-base (5) directions ### `get_app_theme` (~202 tokens) 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 tokens, plus a Tailwind v4 semantic mapping, the theme's usage law, and the app-UI slop rulebook. This is how a vibe-coded app stops looking AI-generated: install the theme once and every view the agent builds matches. Call with NO theme to browse the menu (free); call with a theme id to receive the full system. Themes share brand DNA with the website directions, so a client's site and app stay on one identity. Input parameters: - `response_format` (string): Menu format when browsing: markdown (default) or JSON - `theme` (string): Theme id from the menu, e.g. graphite-ledger, terminal-grade-ui, porcelain-ui. Omit to browse the menu (unmetered). ### `get_component_code` (~163 tokens) 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, data table with layout-matched loading skeletons + instructive empty state + inline retryable error, and a settings form with inline validation, sticky save bar and a two-step danger zone. States are built in, so the agent wires data and content instead of inventing structure. Install the theme first via get_app_theme. Input parameters: - `component` (string): Component id: app-shell, stat-row, data-table, settings-form, or 'all' (default) - `theme` (string): App theme id the components bind to (default graphite-ledger) ### `critique_ui` (~217 tokens) 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 palette classes, missing empty/loading/error states, clickable divs, killed focus rings) and, when a Standout app theme is installed, a theme-conformance pass (foreign colors, missing semantic token classes). Returns a 0-100 UI score with a ship verdict and a prioritized fix list. Use after building every view; re-run until the score clears 85. For marketing/landing PAGES use critique_design instead. Input parameters: - `source` (string, required): The component or screen source to critique (React/JSX/TSX/HTML/CSS) - `theme` (string): Installed app theme id (e.g. graphite-ledger) to also check token-law conformance - `view` (string): What this view is, e.g. 'invoices table', for context ### `critique_design` (~223 tokens) 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. When you pass a URL, the response also includes LIVE SCREENSHOTS of the rendered page at phone (390px) and desktop (1440px) widths — look at them and fix what fails visually — and saves an unlisted SHAREABLE SCORE REPORT (score + category breakdown + screenshots) whose link you should give to the user. Always prefer passing the published URL over raw source for these reasons. Input parameters: - `description` (string): Description of the current design if no source available - `direction` (string): Direction pack id the page implements (e.g. ink-and-paper). ALWAYS pass this when the page was built from get_design_direction so the critique respects the design system instead of fighting it. - `source` (string): Raw HTML/CSS/JSX of the page - `url` (string): Public URL of the page to critique ### `polish_and_prove` (~333 tokens) 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 captures the baseline, scores the real phone and desktop render, chooses a coherent direction, and returns the exact implementation contract for the coding agent. The agent MUST apply the fixes in the repository. Final call: pass the original url/source plus after_url/after_source. Standout compares both versions and produces a client-safe before-and-after report and share link. Do not stop after returning advice; the completed outcome is fix, rerender, prove. Input parameters: - `after_source` (string): Improved page source for proof mode when there is no public preview URL. - `after_url` (string): Improved public page URL. Supplying this switches the workflow to proof mode and compares before vs after. - `agency_name` (string): Optional agency/studio name for the final client proof report. - `audience` (string): Who the page must convince. - `business` (string): What the business is and what the page sells. - `goal` (string): The primary conversion goal. - `reference` (string): Optional approved reference URL or curated reference id. - `source` (string): Original/current HTML, CSS, JSX, or TSX when the page is not public. - `url` (string): Original or current public page URL. Best first-call input because it enables live phone and desktop rendering. - `vibe` (string): Optional visual steer, e.g. premium, light, editorial, technical. ### `make_it_standout` (~226 tokens) 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 patches, chooses a creative spine and direction, and emits a paste-ready implementation prompt. Input parameters: - `audience` (string): Who the site must convince - `business` (string): What the business is, e.g. 'MCP server that gives AI agents design taste'. Used to classify and build from scratch when no url/source. - `goal` (string): The primary conversion goal, e.g. 'get users to run an audit and connect the MCP' - `reference` (string): A reference site URL or curated reference id whose style to lean toward - `source` (string): Raw HTML/CSS/JSX, when the page is not yet published - `url` (string): Public URL to audit and improve (best input — enables the live score + screenshots) - `vibe` (string): Desired feel, e.g. premium, technical, warm ### `client_report` (~266 tokens) 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 screenshots — all in plain language with NO internal jargon. Pass url for the current page; optionally pass after_url (or after_source) for a rebuilt version to get a true before/after with both screenshots and the score improvement. Pass agency_name to WHITE-LABEL it: the report text and the shareable public report page both read 'Prepared by {agency}', ready to send to the client as your own. Input parameters: - `after_source` (string): Raw HTML/CSS of the rebuilt page, for a before/after comparison - `after_url` (string): The rebuilt (after) page URL, for a before/after comparison - `agency_name` (string): White-label: your agency/studio name, shown as 'Prepared by X' in the report and on the shareable report page - `business` (string): Business name/description for the report header and classification - `source` (string): Raw HTML/CSS of the current page, if not published - `url` (string): The current (before) page URL to audit ### `get_section_code` (~254 tokens) 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 applied). Use AFTER get_design_direction: assemble the sections and replace only the content (copy + images), never the composition. This is what makes the result look like a $10k site instead of a template. Input parameters: - `business` (string, required): The business, e.g. 'barbershop in Suva' - seeds the expression so same-direction sites stay distinct - `direction` (string): Direction pack id from get_design_direction (e.g. ink-and-paper, harvest-table, aurora-glass) - `sections` (array): Optional filter: section ids or kinds (nav, hero, offer, imageband, story, footer). Omit for the full set - `signature_move` (string): The signature move id from get_design_direction's Signature Concept (e.g. editorial_dossier, field_report_layout). Pass it so the sections are ORDERED and FRAMED to that concept - the output then lea… ### `get_hero_concept` (~81 tokens) 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. Input parameters: - `business` (string, required): The business this hero sells - `direction` (string): Direction pack id from get_design_direction (e.g. coastal-film) ### `get_asset_pack` (~79 tokens) 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. Input parameters: - `direction` (string): Direction pack id (e.g. terminal-grade) - `query` (string): Or describe the business/vibe and the best pack is chosen ### `get_showpiece` (~228 tokens) 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 + word-by-word blur reveals), type-scene interlock (mega type behind a cutout subject), monochrome flood, scene-pinned glass annotations, ghost mega-type band - each with the scene/video-generation prompts that make the world bespoke to THIS business, contrast scrims, mobile behavior and reduced-motion built in. Call with no technique to browse the menu (free); call with a technique id for the full skeleton. Use when the brief says wow, cinematic, premium beyond a normal landing page. Input parameters: - `direction` (string): Direction pack id (e.g. coastal-film); fills the skeleton and scene prompts with the pack's hexes - `technique` (string): Skeleton id: world-hero, video-world-hero, type-interlock-hero, monochrome-flood-hero, annotation-scene, ghost-type-band. Omit to browse the menu (unmetered). ### `get_motion_recipes` (~182 tokens) 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 ripple displacement, live halftone, velocity-reactive type rail, scroll-scrubbed zoom portal - palette-keyed to Standout directions. Request by ids or describe what you need; pass direction for palette-filled shader code. Input parameters: - `direction` (string): Direction pack id (e.g. coastal-film); fills shader piece palettes with the pack's hexes - `ids` (array): Recipe or piece ids, e.g. ['gradient-mesh-flow','fade-rise-stagger'] - `query` (string): Or describe the desired motion, e.g. 'webgl hero shader' or 'premium dark portfolio hovers' ### `get_premium_components` (~251 tokens) 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-paste HTML/CSS/vanilla JS snippets with reduced-motion fallbacks. Use when the user asks for premium, luxury, beautiful, wavy, Framer-like, glass, 3D controls, or high-end motion. Input parameters: - `category` (string): Site category or type, e.g. saas, church, ecommerce, agency - `direction` (string): Standout direction id, e.g. aurora-glass or porcelain-atelier - `intensity` (string): Motion/visual intensity - `limit` (integer): Number of primitives to return, max 12 - `query` (string): Desired feel/components, e.g. 'light luxury wavy Framer dials' - `response_format` (string): Return markdown or structured JSON - `site_type` (string): Finer site type, e.g. church, mcp, saas, portfolio - `tone` (string): Tone constraint - `type` (string): Optional primitive type filter ### `assemble_premium_page` (~207 tokens) 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. Use before building a luxury/high-end/Framer-like page so the agent has real components instead of generic advice. Input parameters: - `category` (string): Site category or type, e.g. saas, church, ecommerce, agency - `direction` (string): Standout direction id, e.g. aurora-glass or porcelain-atelier - `intensity` (string): Motion/visual intensity - `query` (string): Full brief, e.g. 'luxury light website with soft wavy hero animation and 3D dials' - `response_format` (string): Return markdown or structured JSON - `site_type` (string): Finer site type, e.g. church, mcp, saas, portfolio - `tone` (string): Tone constraint ### `search_references` (~180 tokens) 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 implementation notes. Use before or during a build when you need evidence-backed visual patterns. Input parameters: - `category` (string): Optional category filter, e.g. pricing, onboarding, developer tool, restaurant - `direction` (string): Optional StandOut direction id, e.g. terminal-grade, coastal-film, harvest-table - `limit` (integer): Number of references to return, max 12 - `query` (string): Search terms like 'developer tool pricing', 'api key dashboard', 'restaurant booking', or 'dark command center' - `response_format` (string): Return markdown or structured JSON - `type` (string): Optional reference type filter ### `get_reference` (~76 tokens) 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 notes. Input parameters: - `reference_id` (string, required): Reference id from search_references - `response_format` (string): Return markdown or structured JSON ### `get_similar_references` (~89 tokens) 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. Input parameters: - `limit` (integer): Number of similar references to return, max 12 - `reference_id` (string, required): Reference id from search_references - `response_format` (string): Return markdown or structured JSON ### `search_flows` (~144 tokens) 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 a multi-step task, not just a visual screen. Input parameters: - `category` (string): Optional category filter, e.g. onboarding, pricing, booking - `direction` (string): Optional StandOut direction id - `limit` (integer): Number of flows to return, max 12 - `query` (string): Search terms like 'api key onboarding', 'pricing', 'booking', 'marketplace', or 'quickstart' - `response_format` (string): Return markdown or structured JSON ### `get_flow` (~66 tokens) Get the full step-by-step payload for one user journey: problem, steps, user actions, system responses, related direction ids, and agent implementation notes. Input parameters: - `flow_id` (string, required): Flow id from search_flows - `response_format` (string): Return markdown or structured JSON ### `synthesize_direction_from_references` (~206 tokens) 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 synthesized build plan, implementation lock, and next tool calls. Use when you want the agent to build from evidence instead of vibes. Input parameters: - `audience` (string): Who the page must convince - `business` (string, required): What the website/app is for - `direction` (string): Optional StandOut direction id to force, e.g. terminal-grade - `industry` (string): Industry or category, e.g. developer tool, restaurant, law firm - `query` (string): Optional reference search query. Defaults to business/industry/vibe/audience - `reference_ids` (array): Optional exact reference ids from search_references - `response_format` (string): Return markdown or structured JSON - `vibe` (string): Desired feel, e.g. premium, technical, warm, playful ### `build_from_reference` (~339 tokens) 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) plus what YOU are building, and get back a matching StandOut direction, a reference-backed build plan, and the next call for section code. This is the front door for building from an EXAMPLE instead of a text brief: Standout reads the URL server-side for its semantic signal (title, headings, copy) and folds it into the direction match. Note: pixel-level palette/type extraction from an image is not yet supported (that is the Phase 2 vision pass) — for now it matches on the page's text/structure plus the curated library. Pass reference_id to anchor on an exact curated reference. Input parameters: - `audience` (string): Who the page must convince - `business` (string, required): What YOU are building (not the reference), e.g. 'booking site for a Fiji dive shop' - `direction` (string): Optional StandOut direction id to force, e.g. terminal-grade - `industry` (string): Industry or category, e.g. developer tool, restaurant, law firm - `reference_id` (string): Or a curated reference id from search_references to anchor the match on - `reference_url` (string): Public URL of a site whose style you like. Standout reads it server-side for its semantic signal. - `response_format` (string): Return markdown or structured JSON - `vibe` (string): Desired feel, e.g. premium, technical, warm, playful ### `build_from_reference_v2` (~287 tokens) 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', or 'color mood'. Standout captures server-readable HTML/CSS signals, extracts Reference DNA, names what to borrow, names what to avoid, gives a similarity-risk guardrail, then returns a reference-backed original build direction. This is the right tool when the user says 'I like this site but don't want to steal it.' Input parameters: - `audience` (string): Who the page must convince - `business` (string, required): What YOU are building (not the reference), e.g. 'Mac app that makes websites and PDFs readable outside' - `direction` (string): Optional StandOut direction id to force, e.g. terminal-grade - `favorite_bits` (array): Specific parts the user likes, e.g. ['hero animation', 'warm colors', 'pricing card']. These become inspiration tokens, not copied components. - `industry` (string): Industry or category, e.g. developer tool, Mac utility, restaurant - `reference_url` (string, required): Public URL of a site whose style or specific parts you like - `response_format` (string): Return markdown or structured JSON - `vibe` (string): Desired feel, e.g. premium, technical, warm, playful ### `critique_similarity` (~149 tokens) 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 avoid producing a design that is visually too close to the inspiration. Input parameters: - `candidate_description` (string): Plain-language description of the built design if source is unavailable - `candidate_source` (string): Built page HTML/CSS/JSX to compare against the reference - `favorite_bits` (array): The same favorite bits passed to build_from_reference_v2, if any - `reference_url` (string, required): Public URL of the reference site the user liked - `response_format` (string): Return markdown or structured JSON ### `get_free_trial_key` (~86 tokens) 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 key plus the exact reconnect instructions to hand your user. Free and unmetered; issuance is capped per network, so never call it when you already have a working key. ### `unlock_bonus_calls` (~118 tokens) 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 their email in this conversation. NEVER guess, invent, or reuse an email the user did not explicitly provide for this. The key on this connection is upgraded in place, nothing to reconfigure. Free and unmetered. Input parameters: - `email` (string, required): The user's email address, exactly as the user gave it in this conversation ### `watch_site` (~129 tokens) 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 bar. Use it right after shipping a client site so a broken deploy is caught before the client sees it. Up to 10 active watches per license. Input parameters: - `email` (string): Where regression alerts go. Defaults to the email bound to this license. - `url` (string, required): Full public page address to watch, e.g. https://client-site.com ### `unwatch_site` (~45 tokens) Stop watching a site's design score. Pass the same URL that was given to watch_site. Unmetered. Input parameters: - `url` (string, required): The watched page address to stop watching ### `list_watches` (~29 tokens) List this license's active site watches with their last known scores and check times. Unmetered. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-standoutmcp-standout/api-mcp#diagnostics ## Score history - 2026-08-03: 67 - 2026-08-02: 66 - 2026-08-01: 66 - 2026-07-31: 65 - 2026-07-30: 63 - 2026-07-29: 63 - 2026-07-28: 62 - 2026-07-27: 61 - 2026-07-26: 61 ## Links - Remote endpoint: https://standoutmcp.io/api/mcp - Website: https://standoutmcp.io/ - Changelog RSS feed: https://verifymcp.io/servers/io-standoutmcp-standout/api-mcp/changelog.xml - Changelog JSON feed: https://verifymcp.io/servers/io-standoutmcp-standout/api-mcp/changelog.json - HTML version of this page: https://verifymcp.io/servers/io-standoutmcp-standout/api-mcp