# Raven (remote · mcp.ravenmcp.ai) Design intelligence for coding agents: audits, design systems, and a taste profile agents consult. - Trust score: 73/100 (medium) - Change this week: +5 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-03 ## Components - remote · `mcp.ravenmcp.ai`: 73/100 (this document), [markdown](https://verifymcp.io/servers/ai-ravenmcp-raven-mcp/api-mcp.md), [page](https://verifymcp.io/servers/ai-ravenmcp-raven-mcp/api-mcp) - npm · `raven-mcp`: 33/100, [markdown](https://verifymcp.io/servers/ai-ravenmcp-raven-mcp/raven-mcp.md), [page](https://verifymcp.io/servers/ai-ravenmcp-raven-mcp/raven-mcp) ## Channel facts - Endpoint: `https://mcp.ravenmcp.ai/api/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `2.3.0` ## 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**: 80/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 61/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (fair). - Context-footprint check failed: tool/resource definitions use about 9256 tokens (~205/item across 45 items; 45 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**: 98/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 94% 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 ai-ravenmcp-raven-mcp https://mcp.ravenmcp.ai/api/mcp ``` ### Codex ```toml [mcp_servers.ai-ravenmcp-raven-mcp] url = "https://mcp.ravenmcp.ai/api/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "ai-ravenmcp-raven-mcp": { "type": "remote", "url": "https://mcp.ravenmcp.ai/api/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add ai-ravenmcp-raven-mcp --url https://mcp.ravenmcp.ai/api/mcp --transport streamable-http ``` ### Hermes ```yaml mcp_servers: ai-ravenmcp-raven-mcp: url: "https://mcp.ravenmcp.ai/api/mcp" ``` ### Other ```json { "mcpServers": { "ai-ravenmcp-raven-mcp": { "type": "http", "url": "https://mcp.ravenmcp.ai/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 73, −1) - [security] Tool “list_content_systems” rewrote its description, which is the text the model reads - [functional] Schema quality: good → fair - [cosmetic] “get_content_system” reworded the description of “id” ### 2026-08-01 (score 74, +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 73, +3) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-30 (score 70, +2) No change was recorded against any check on this day. Stability & Change Management went from 7 to 13. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-07-28 (score 68, 0) - [functional] Server version: 2.2.9 → 2.3.0 ### 2026-07-27 (score 68, +15) - [security improvement] Authorization: unverified → partial - [functional improvement] Stability: unverified → 0.03 - [functional] First check of Schema quality: 100 - [functional] Schema quality: poor → good - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server - [functional] Server version: 2.2.8 → 2.2.9 ### 2026-07-26 (score 53) First indexed and scored. ## MCP tools (45) ### `get_principles` (~250 tokens) Get design principles relevant to a UI context. Returns usability heuristics, laws of UX, Gestalt principles, accessibility requirements, typography rules, and color theory — matched to what you're designing. Input parameters: - `category` (string): Filter to category: nielsen-heuristics, laws-of-ux, gestalt, accessibility, typography, color-theory, mobile-ux, d4d, color-systems, spacing-systems - `context` (string, required): What you're designing (e.g. 'signup form', 'pricing page', 'mobile nav', 'dark dashboard') - `format` (string): Output format: full (all details), checklist (implications + violations), brief (just summary). Default: full - `platform` (string): Platform context. 'ios' returns Apple HIG principles (Dynamic Type, 44pt targets, SF Symbols, safe areas, dark-mode, haptics, App Review privacy); 'react-native' returns RN principles (44/48pt+hitSlo… ### `get_pattern` (~159 tokens) Get proven UI/UX patterns for a specific design type. Returns do's, don'ts, evidence, and checklists for signup flows, pricing pages, navigation, forms, landing pages, dashboards, modals, empty states, error states, loading states, CTAs, social proof, and mobile conversion. Input parameters: - `goal` (string): Filter by primary goal - `platform` (string): Filter patterns by platform context - `type` (string, required): Pattern type (e.g. 'signup-flow', 'pricing-page', 'navigation', 'forms', 'landing-page', 'dashboard', 'modals-dialogs', 'empty-states', 'error-states', 'loading-states', 'cta', 'social-proof', 'mobil… ### `get_business_strategy` (~70 tokens) Get business and monetization strategies for digital products. Covers monetization models, retention strategies, onboarding optimization, growth mechanics, and product metrics frameworks. Input parameters: - `stage` (string): Company stage for contextual filtering - `type` (string, required): Strategy type: monetization, retention, onboarding, growth, metrics ### `evaluate_design` (~187 tokens) Evaluate a design description against UX principles. Returns relevant principles, potential violations, and improvement suggestions. Input parameters: - `after_screenshot` (string): Base64 PNG of the AFTER state. When both before+after are provided, returns a structured pixel diff with fix_confirmed. - `before_screenshot` (string): Base64 PNG of the BEFORE state - `compact` (boolean): Return only ids+names for matched principles/patterns (drop their full bodies) plus counts and any before/after diff. Default false. Use when the full principle library payload would blow the tool-re… - `context` (string): What the design is (e.g. 'pricing page for SaaS product') - `description` (string): Description of the design to evaluate - `goals` (array): What to evaluate for (e.g. ['conversion', 'accessibility', 'mobile-usability']) ### `search_knowledge` (~85 tokens) Search across all design principles, UI patterns, and business strategies. Use when you need to find specific guidance or don't know which category to look in. Input parameters: - `layer` (string): Which layer to search: principles, patterns, business, or all (default) - `query` (string, required): Search term (e.g. 'touch targets', 'pricing psychology', 'color contrast') ### `get_checklist` (~144 tokens) Get a pre-publish checklist for a specific UI type. Returns actionable yes/no items to verify before shipping. Input parameters: - `platform` (string): Platform context for platform-specific checks. 'ios' = native SwiftUI/iOS (Apple HIG); 'react-native' = RN/Expo (iOS HIG + Android Material: 44/48pt+hitSlop, accessibilityLabel/Role, font scaling, Sa… - `type` (string, required): What you're shipping (e.g. 'signup form', 'pricing page', 'dashboard', 'landing page', 'modal') ### `get_d4d_framework` (~69 tokens) Get the Design for Delight (D4D) framework templates. Returns customer problem statement, ideal state, hypothesis, LOFA, and experiment templates for structured product thinking. Input parameters: - `stage` (string): Which stage of the D4D loop to return. Default: full (all stages) ### `list_design_systems` (~73 tokens) Browse available design systems for tokens. Filter by category (fintech, productivity, developer, component-library, design-system) or search by name. Input parameters: - `category` (string): Filter by category: fintech, productivity, developer, component-library, design-system - `search` (string): Search by name or description ### `get_design_system` (~130 tokens) Get design tokens for a specific design system. Returns colors, typography, spacing, radii, elevation, and motion tokens in W3C DTCG, CSS custom properties, or flat format. Input parameters: - `format` (string): Output format: dtcg (W3C standard), css (custom properties), flat (key-value). Default: dtcg - `group` (string): Filter to a token group: color, color-dark, color-light, typography, spacing, radius, elevation, motion - `id` (string, required): Design system ID (e.g. 'stripe', 'linear') ### `compose_system` (~58 tokens) Mix tokens from different design systems to create a custom composite. Example: Linear's colors + Stripe's typography. Input parameters: - `compositions` (array, required): Array of system-group pairs to compose - `format` (string): Output format. Default: dtcg ### `audit_page` (~479 tokens) Audit HTML/CSS against Raven's design quality standards. Checks typography (min 13px, weight 400+, modular-scale heading ratios, line-height consistency), accessibility (WCAG touch targets, alt text, contrast), responsive patterns (flexbox over grid, clamp sizing, max-width containers), style guide compliance (CSS custom properties, no bare hex), and visual rhythm (4/8px spacing grid, tight spacing scale, palette size). Pass containerMaxWidth (your design system's canonical container token, in px) to make the max-width check token-aware — it then flags containers that diverge from your system (too narrow OR too wide) instead of a generic 1200px heuristic. Returns pass/fail per check with specific fix instructions. Input parameters: - `adversarial_verify` (boolean): After generating findings, independently re-check each against the live DOM/network and tag it confirmed / likely-artifact / inconclusive. Surfaces a debunked_count. - `compact` (boolean): Return only the decision-grade signal — score, grade, summary, errors, warnings, fix_priority — and drop the embedded base64 screenshot and the passes list (replaced by passes_count). Default false.… - `containerMaxWidth` (number): Your design system's canonical content-container width in px (e.g. 1152). When set, the responsive/max-width check flags divergence from this token instead of using the generic 1200px heuristic. - `html` (string): The full HTML content of the page to audit - `interactions` (array): Before capturing, fire each interaction in order (hover/click/focus the selector, then wait delay_ms). Captures the resulting dynamic state — e.g. an on-hover theme-toggle wash invisible to a static… - `scroll_settle` (boolean): Before capturing, step through the page with short pauses so IntersectionObserver/whileInView reveals fire, then return to the top and settle. Also plays preload=none videos. Prevents blank-section f… - `strict` (boolean): Strict mode — also flags warnings as failures. Default: false - `url` (string): If set, Raven launches headless chromium, renders the page, and audits the RENDERED DOM. - `viewport` (object) ### `score_page` (~241 tokens) Score an HTML/CSS page across 7 design categories (Structure, Typography, Color & palette, Spacing & rhythm, Accessibility, Responsive layout, Design tokens), each rated 0–10. Scores are derived deterministically from the same checks as audit_page — no browser required. Pass html directly, or pass url to have Raven launch headless chromium, render the page, and score the RENDERED DOM. Also returns the same overall 0–100 score and A–D grade audit_page produces, the weakest category, and the three categories Raven does not mechanically assess (brand, conversion, motion) with guidance on which tools to use for those. Input parameters: - `containerMaxWidth` (number): Your design system's canonical content-container width in px (e.g. 1152). Forwarded to the responsive/max-width check. - `html` (string): The full HTML content of the page to score. - `strict` (boolean): Strict mode — count warnings as failures in the overall score. Default: false. - `url` (string): If set, Raven launches headless chromium, renders the page, and scores the RENDERED DOM. ### `audit_parity` (~111 tokens) Compare iOS vs Android element snapshots against a checklist of named spatial relationships (vertical centering, baseline/left alignment, equal gap/size, presence, truncation) and flag per-relation match/mismatch/uncertain — catches cross-platform layout drift like status text centered on one platform but top-aligned on the other. Provide ios+android {elements,viewport} snapshots and a checklist[]. Input parameters: - `android` (object, required) - `checklist` (array, required) - `ios` (object, required) ### `audit_ios_a11y` (~117 tokens) Score an accessibility-enriched iOS element snapshot — missing accessibilityLabel/value/traits, sub-44pt tap targets, per-text WCAG contrast, Dynamic Type clipping, and VoiceOver reading order. Provide {elements:[{label,value,hint,traits,role,rect,fontPt,fgColor,bgColor,dynamicTypeClipped}],viewport}. Capture via the AccessibilitySnapshot XCUITest / ios-capture harness. Input parameters: - `elements` (array, required) - `options` (object) - `viewport` (object, required) ### `audit_responsive_visibility` (~162 tokens) Render a URL at multiple breakpoints and flag content elements that are visible on desktop but hidden on mobile (display:none / opacity:0 / visibility:hidden / zero-size). Categorises each flag as 'likely-oversight' (content that vanishes on mobile — the hidden-on-mobile content bug) vs 'intentional' (decorative). Returns a table of selector / hiding-class / mobile-visible / desktop-visible / category. Requires headless chromium. Input parameters: - `breakpoints` (array): Viewport widths in px. Default [390, 768, 1440, 2160] - `url` (string, required): URL to render (http/https or file://) - `viewportHeight` (number): Render height in px. Default 900 ### `audit_contrast` (~139 tokens) Compute WCAG contrast ratios for every text element on a rendered page (pass url) or from a supplied dom_snapshot. Reports AA (4.5:1 normal, 3:1 large) and AAA pass/fail per element and surfaces failing pairs with selector, ratio, and delta-to-pass — replacing manual eyedropper + ratio math. Input parameters: - `dom_snapshot` (array): Pre-collected text elements to score without rendering - `screenshot` (string): Optional base64 PNG for caller reference; ratios are computed from the DOM, not pixels - `url` (string): URL to render and measure (http/https or file://) ### `suggest_contrast_fix` (~163 tokens) Given failing WCAG color pairs, return the MINIMAL color change that clears the target ratio. For each {fg,bg} pair, computes the smallest foreground adjustment (and an alternative background adjustment) that reaches AA/AAA — with the achieved ratio and direction. Feeds directly from audit_contrast's failing pairs: pass them here to get concrete passing values instead of brute-forcing colors by hand. Pure offline math. Input parameters: - `level` (string): WCAG level when targetRatio is not given per-pair. Default AA. - `pairs` (array): Color pairs to remediate. Each: { selector?, fg, bg, fontPx?, bold?, targetRatio? }. fontPx/bold pick the large-text threshold; targetRatio overrides the level. ### `audit_url` (~437 tokens) Layer 0 render-and-capture audit: renders a LIVE URL at each viewport×theme, scroll-settles (fires whileInView/IntersectionObserver reveals; plays preload=none videos), fires hover/click/focus interactions, and captures real pixels + the rendered DOM. Then runs the existing audit_page rule engine, per-element WCAG contrast, responsive-visibility (desktop-shown/mobile-hidden), blank-media detection, sliced-image edge symmetry, and hover-state white-wash detection over the captures. Every finding is tagged confirmed | likely-artifact | inconclusive with its evidence, ranked by severity. This is the tool that catches real-world visual nits invisible to HTML-string/geometry audits: cropped images, blank videos, hover white-wash, sliced exports, and hidden-on-mobile content. Requires headless chromium. Input parameters: - `compact` (boolean): Drop per-capture base64 screenshots; keep findings, counts, and summary. Default false. Use when screenshots would blow the tool-result budget. - `containerMaxWidth` (number): Your design system's canonical container width in px — makes the max-width check token-aware. - `includeScreenshots` (boolean): Include the base64 full-page PNG per capture in the result. Default: false (screenshots are large). - `interactions` (array): Fire each interaction before capture; the resulting state is diffed against baseline to catch hover/click white-wash and obscured content. - `scroll_settle` (boolean): Step through the page with short pauses to fire reveal-on-scroll/IntersectionObserver content, play videos, then return to the top before capture. Default: true - `themes` (array): Themes to toggle (prefers-color-scheme + data-theme/class). Default: ['light','dark'] - `timeoutMs` (number): Per-navigation timeout in ms. Default: 30000 - `url` (string, required): URL to render and audit (http/https or file://) - `viewports` (array): Viewports to render. Default: iphone 393×852, desktop 1440×900, wide 2160×1200 ### `audit_content` (~220 tokens) Evaluate an array of content items (headings, prose, CTAs, labels, captions, metrics, outcomes) against UX-writing principles and deterministic heuristics. Returns a per-item verdict (pass/warn/fail) with matched principle ids, concrete issues grounded in principle text, a before→after rewrite suggestion, and an aggregate summary. Heuristics: metric items must carry a number+unit; cta/label must be action-led and ≤4 words; prose flags passive voice, jargon, and hedging; headings flag filler openers and buzzwords; captions flag duplication of any heading in the batch. Pure offline — no network or browser. Use this instead of evaluate_design when you need per-item content verdicts rather than the principle library. Input parameters: - `goals` (array): Optional content goals (e.g. ['clarity','conversion']); recorded for traceability. - `items` (array, required): Array of content items to audit. - `system` (string): Optional content-system id (e.g. 'ux-writing'); recorded for traceability. ### `audit_typography` (~209 tokens) Audit the typographic SCALE of a rendered page (pass url) or a pre-collected snapshot of text nodes. Emits a focused report: (a) MODULAR SCALE — detects the dominant ratio (~1.2/1.25/1.333/1.5) across distinct font sizes and flags off-scale outliers; (b) LINE-HEIGHT CONSISTENCY — unitless lh/fs ratio per node, identifies the body rhythm and flags outliers; (c) WEIGHT LADDER — distinct weights, flags >4 weights or non-standard CSS values. Returns scale, line_height, weight_ladder, nodes_analyzed, and findings[{rule,severity,selector,message,fix}]. Goes beyond audit_page's pass/fail typography checks. url mode requires headless chromium. Input parameters: - `nodes` (array): Pre-collected text nodes to analyze without rendering. - `url` (string): URL to render and measure (http/https or file://). Requires headless chromium. ### `audit_tap_targets` (~207 tokens) WCAG 2.5.5 / Apple 44pt tap-target audit for the web. Collects every interactive element (a, button, [role=button], input[type=submit/button/checkbox/radio], select, summary, label[for], [onclick], [tabindex>=0]) and emits a PER-ELEMENT fix table for any whose rendered width or height is below the minimum (default 44px): selector, role, visible text, measured w/h, pixel deficit per axis, and a concrete CSS fix. Sorted worst-first. Two modes: pass url (renders in headless chromium, measures real getBoundingClientRect) or pass elements[] snapshot (pure, no browser). Input parameters: - `elements` (array): Pre-collected interactive elements to score without rendering. - `minSize` (number): Minimum tap-target size in px on each axis. Default 44. - `url` (string): URL to render and measure. Requires headless chromium. ### `get_brand_system` (~157 tokens) Get a complete design system for building an app with branding like a specific company. Say 'Make me an app with branding like Spotify' and get the full token set, style guide, and implementation instructions. Matches against 12 known design systems and provides closest match with ready-to-use CSS. Input parameters: - `company` (string, required): The company whose branding to use (e.g. 'Spotify', 'Stripe', 'Apple', 'Linear', 'Airbnb') - `format` (string): Output format: 'css' for CSS variables, 'dtcg' for W3C tokens, 'guide' for full implementation guide. Default: guide - `mode` (string): Color mode preference. Default: based on the system's primary mode ### `generate_design_system` (~265 tokens) Generate a complete, custom design system with full token set. Provide a brand color to auto-generate a harmonious palette, pick a style preset, and export as visual HTML documentation, CSS variables, W3C DTCG JSON, Figma Variables, or SVG palette card. The HTML export is a beautiful, self-contained page suitable for sharing with stakeholders. Input parameters: - `base_system` (string): Start from an existing system as foundation (e.g. 'stripe', 'linear'). Colors will be replaced by brand_color if provided. - `brand_color` (string): Primary brand hex color (e.g. '#FF6B35'). Auto-generates a full harmonious palette using color theory. - `dark_mode` (boolean): Generate dark mode tokens alongside light. Default: true - `format` (string): Export format: html (visual doc page), css (custom properties), dtcg (W3C JSON), figma (Figma Variables JSON), svg (color palette card), all. Default: html - `name` (string, required): Name for the design system (e.g. 'Acme Corp', 'NightOwl') - `style` (string): Aesthetic direction — influences spacing, radii, shadows, motion, and typography. Default: minimal ### `audit_layout` (~115 tokens) Evaluate visual rhythm from a rendered page's geometry. Call with no arguments to get a DevTools snippet to paste into your page — it prints {elements, viewport} JSON. Call again with that JSON to get alignment, gap-rhythm, and optical-balance scores. This is the complement to audit_page for things only visible once rendered. Input parameters: - `elements` (array): Array of element rects captured from the rendered page via the DevTools snippet - `viewport` (object): Viewport dimensions {w,h} at capture time ### `audit_swiftui` (~312 tokens) Audit SwiftUI source against Apple's Human Interface Guidelines. Flags hardcoded .font(.system(size:)) below ~13pt and tiny semantic fonts (.caption/.caption2), hardcoded Color(red:green:blue:)/hex instead of asset-catalog or semantic system colors, an empty/undefined AccentColor, interactive frames below 44×44pt, and ad-hoc spacing off the 4/8-pt grid. Rewards semantic Dynamic Type fonts, semantic system colors, SF Symbols, and flexible frames. iOS-native checks only — no web/CSS rules. Returns pass/fail per check with fix instructions. Input parameters: - `accent_color_contents` (string): Optional raw Contents.json of AccentColor.colorset. When provided, the tool verifies AccentColor actually defines color components (flags an empty/undefined accent color as an error). - `profile` (string): Taste profile owning the binding. Omit to search all stored profiles for one bound to the project. - `project` (string): Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes, each note is verified against the source (animation/material/haptic/font A… - `source` (required): SwiftUI source — a single file/view as a string, or an array of file contents. Concatenated before analysis. - `strict` (boolean): Strict mode — also count warnings as failures for grading. Default: false ### `audit_screen` (~346 tokens) Audit a rendered mobile screen (iOS or Android) from a view-hierarchy/accessibility snapshot. Call with no arguments for the expected snapshot shape and how to capture it. Pass platform:"android" to score against the 48dp Material touch minimum and Material muted roles (onSurfaceVariant/outline = warn not fail); default platform:"ios" scores 44pt and treats secondaryLabel/tertiaryLabel as platform-standard. Both score touch targets, contrast, and visual rhythm (alignment, gap consistency, optical balance). Same return shape as audit_page. Input parameters: - `elements` (array): Elements captured from the rendered screen via an accessibility/view-hierarchy snapshot - `platform` (string): Target platform — 'ios' (default, 44pt minimum, iOS semantic colors) or 'android' (48dp minimum, Material semantic roles) - `profile` (string): Taste profile owning the binding. Omit to search all stored profiles for one bound to the project. - `project` (string): Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes and a screenshot is passed, the screenshot's pixels verify the color-scheme… - `screenshot` (string): Optional base64 PNG of the screen, for the caller's reference. Geometry is scored from the snapshot, not decoded pixels. - `scroll_settle` (boolean) - `viewport` (object): Screen size in pt (iOS) or dp (Android) at capture time, e.g. {w:393,h:852} iPhone 15, {w:412,h:915} Pixel ### `audit_ios_screen` (~308 tokens) Audit a rendered iOS screen from a view-hierarchy/accessibility snapshot (and optional screenshot). Alias of audit_screen with platform:"ios". Call with no arguments for the expected snapshot shape. Call with {elements:[{label,rect:{x,y,w,h},role,fontPt,fgColor,bgColor}],viewport:{w,h}} to score 44×44pt touch targets, contrast (with iOS secondaryLabel/tertiaryLabel treated as platform-standard — warn not fail), and visual rhythm (alignment, gap consistency, optical balance) in points. Same return shape as audit_page. Input parameters: - `elements` (array): Elements captured from the rendered screen via an accessibility/view-hierarchy snapshot - `profile` (string): Taste profile owning the binding. Omit to search all stored profiles for one bound to the project. - `project` (string): Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes and a screenshot is passed, the screenshot's pixels verify the color-scheme… - `screenshot` (string): Optional base64 PNG of the screen, for the caller's reference. Geometry is scored from the snapshot, not decoded pixels. - `viewport` (object): Screen size in pt (iOS) or dp (Android) at capture time, e.g. {w:393,h:852} iPhone 15, {w:412,h:915} Pixel ### `audit_ios_privacy` (~299 tokens) Audit an iOS or React Native/Expo app's privacy posture for App Review and user trust. Reads a native Info.plist XML OR an Expo app.json (managed Expo apps have no Info.plist) — plus optional PRIVACY.md, entitlements, and source. Flags: NS*UsageDescription strings that are vague/missing or contradict the code (e.g. a HealthKit write claim the code never fulfills), entitlements/permissions and Android permissions the app doesn't use, ATS cleartext exceptions and non-HTTPS endpoints, secrets/keys shipped in the bundle or app.json, and default data-egress paths not disclosed at the point of choice (a pre-selected 'Recommended' option that silently sends personal data to a server). Same return shape as audit_page. Input parameters: - `app_json` (string): Expo app.json / app.config JSON (managed RN). Its expo.ios.infoPlist, expo.android.permissions, plugins, and extra are audited. - `entitlements` (string): Optional .entitlements XML - `info_plist` (string): Raw Info.plist XML (native iOS / bare RN). Provide this OR app_json. - `privacy_md` (string): Optional PRIVACY.md / privacy policy text to cross-reference against declared permissions and default behavior - `source` (string): Optional concatenated source (Swift or JS/TS) — enables code-vs-declaration contradiction checks and default-egress detection ### `audit_rn` (~340 tokens) Audit React Native / Expo source (JSX/TSX + StyleSheet) against the iOS HIG + Android Material conventions RN must satisfy. Flags touchables missing accessibilityLabel/accessibilityRole, touchables below 44pt without hitSlop, allowFontScaling={false}, fontSize below ~13, screens without SafeAreaView, and (for multi-mode apps) hardcoded colors with no useColorScheme/Appearance dark-mode handling. Rewards SafeAreaView, hitSlop, Platform-aware code, and a theme. RN-native checks only — no web/CSS or SwiftUI rules. Same return shape as audit_page. (RN renders to native widgets, so audit_ios_screen scores the rendered screen.) Input parameters: - `color_scheme` (string): The app's declared appearance (Expo app.json userInterfaceStyle). 'light' or 'dark' means single-mode by design — the dark-mode adaptation check is then suppressed. Default: automatic. - `profile` (string): Taste profile owning the binding. Omit to search all stored profiles for one bound to the project. - `project` (string): Project identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes, each note is verified against the source (Animated/Reanimated, BlurView, h… - `source` (required): React Native source — a single screen/component as a string, or an array of file contents. Concatenated before analysis. - `strict` (boolean): Strict mode — also count warnings as failures for grading. Default: false ### `list_content_systems` (~87 tokens) Browse available content design systems — brand voice and tone guides (Conversational Product Voice, GOV.UK, Shopify Polaris, Atlassian). Filter by category or search by name. Input parameters: - `category` (string): Filter by category: marketing-saas, government, commerce-saas, productivity-saas, fintech - `search` (string): Search by name, description, or tag ### `get_content_system` (~105 tokens) Get a brand's content design system — voice attributes, tone shifts by context, vocabulary (use/avoid/never), grammar rules, content patterns for errors/empty-states/buttons/etc., and inclusive language guidance. Input parameters: - `id` (string, required): Content system ID (e.g. 'conversational-product-voice', 'gov-uk', 'shopify-polaris', 'atlassian') - `section` (string): Return just one section. Default: all. ### `get_content_principles` (~127 tokens) Get UX-writing principles — clarity over cleverness, active voice, error-message anatomy, inclusive language, voice vs tone, and more. Filter by the writing context (e.g. 'error messages', 'notifications', 'form labels'). Input parameters: - `context` (string): What you're writing for (e.g. 'error messages', 'onboarding copy', 'empty state', 'notification'). Omit to get all UX-writing principles. - `format` (string): Output format: full (all details), checklist (implications + violations), brief (just summary). Default: full ### `get_content_pattern` (~58 tokens) Get content design patterns — copy recipes for error messages, empty-state copy, notifications, and form validation. Returns do's, don'ts, good/bad examples, evidence, and a checklist. Input parameters: - `type` (string, required): Content pattern type ### `get_research_method` (~128 tokens) Get research method details — qualitative (interviews, contextual inquiry, diary, field, intercept), quantitative (surveys, analytics, A/B tests, benchmarking, clickstream), or usability (moderated, unmoderated, 5-second, card sort, tree test, heuristic eval). Returns specific protocols, do/don't guidance, evidence, and a checklist. Use when the user is designing a study or asking how to measure something. Input parameters: - `category` (string): Which family of methods. Default: all. - `search` (string): Search within methods by name or description. ### `get_metrics_framework` (~132 tokens) Get a product-metrics framework — HEART (Google), AARRR/Pirate (Dave McClure), North Star Metric, Conversion Funnel, RICE Scoring, or OKRs. Returns structure, when-to-use, pitfalls, and examples. Use when the user asks 'how should we measure success?' or 'what metrics should we track?' Input parameters: - `id` (string): Framework id (heart, aarrr, north-star-metric, conversion-funnel, rice-scoring, okrs). Omit to list all. - `search` (string): Search for a framework by name or summary. ### `get_service_pattern` (~85 tokens) Get a service design pattern — service blueprinting, human handoff, signup-as-service, omnichannel continuity, or moments of truth / recovery. Returns patterns, do/don't guidance, evidence, and a checklist. Use when the user is designing a service flow, escalation, cross-channel experience, or moment of truth. Input parameters: - `type` (string, required): Service design pattern type ### `get_service_standard` (~59 tokens) Get the GOV.UK Service Standard — 14 points the UK government uses to assess whether a public service is ready to launch. Widely applicable as a rigorous service-quality checklist beyond government. Use when the user asks how to evaluate a whole service. ### `generate_service_blueprint` (~255 tokens) Render a service blueprint as a self-contained HTML page. Supports two modes: (1) classic Shostack single-actor blueprint — user action, frontstage, backstage, support, evidence, pain/delight; (2) two-actor HI-loop blueprint — when `actors` is supplied, renders two swim lanes with a line of interaction between them (e.g. customer ↔ lawyer, patient ↔ doctor, buyer ↔ agent). Each actor gets their own actions, frontstage (what they see), and evidence. Optionally accepts an ideal-state to render side-by-side with the current state. Input parameters: - `actors` (object): Omit for classic single-actor Shostack blueprint. Provide to render a two-swim-lane HI-loop blueprint with a line of interaction between the two sides. - `current` (array, required): The current-state blueprint as an array of steps - `ideal` (array): Optional ideal-state blueprint — if provided, output shows current AND ideal side-by-side - `service_name` (string, required): Name of the service (e.g. 'Free trial signup', 'Client intake', 'Restaurant reservation') - `subtitle` (string): Short description or context line under the title ### `get_brand_principles` (~146 tokens) Get brand and visual-design principles — logo usage (clear space, min sizes, variants, placement, restraint), gradient usage (hierarchy, palette, contrast, trend vs signature), imagery (consistency, representation, purpose), visual hierarchy, and brand-as-system thinking. Use when the user asks about branding, logos, gradients, imagery, visual consistency, or how to treat a brand across surfaces. Input parameters: - `format` (string): Output format. Default: full. - `topic` (string): Filter by topic: 'logo', 'gradient', 'imagery', 'hierarchy', 'system', or a freeform search term. Omit to return all brand principles. ### `get_brand_trends` (~81 tokens) Get current brand and visual-design trends — what's working in 2026 and where each trend fits or fails. Includes bento grids, monospace type, neon-on-dark-glass, generative patterns, brutalism rebound, AI-generated imagery, lowercase/mixed case. Each trend is time-stamped — treat as a calibration signal, not a prescription. ### `list_creative_models` (~105 tokens) Browse Raven's provider-agnostic creative model catalog. These are capability slots for image, video, 3D, audio, character consistency, and creative analysis. Use a configured RAVEN_CREATIVE_RUNNER to route jobs to any local CLI or API wrapper. Input parameters: - `capability` (string): Filter by capability, e.g. product-photoshoot, text-to-video, brand-kit, ugc-ad. - `media_type` (string): Filter by media type. ### `list_creative_presets` (~70 tokens) Browse Raven creative presets for product photoshoots, marketplace cards, UGC ads, TV spots, cinematic reveals, social launch packs, storyboards, and infographics. Input parameters: - `media_type` (string): Filter presets by media type. - `search` (string): Search preset name or description. ### `score_creative` (~113 tokens) Score a creative prompt, script, or ad concept for hook strength, benefit clarity, product signal, call-to-action, channel fit, audience fit, and brand fit. This is a transparent heuristic, not a proprietary prediction model. Input parameters: - `audience` (string): Target audience if not in a brand profile. - `brand_profile_id` (string): Local Raven brand profile ID. - `channel` (string): Target channel. - `creative_text` (string, required): Prompt, script, ad copy, or creative concept to score. ### `audit_consistency` (~261 tokens) Audit multiple pages for cross-page consistency of content-container width and hero heading tier. Pass ≥2 pages ({name, html}) collected from different routes on the same site. Infers the canonical (modal) value from the corpus when no token is supplied, so you need not know the project's design token in advance. Flags the issue #9 single-blob blind spot: pages that each pass audit_page but silently disagree with each other on container width or hero size class. Returns per-page extraction (container_px, container_classes, hero_classes, signatures), consistency dimensions with reference values, outlier page names, issues[], score (100/50/0 → A/C/D), and a plain-text summary. Pure offline — no browser, no network. Input parameters: - `container_token` (number): Project's canonical container width in px (e.g. 1152). When supplied, container divergence is measured against this token rather than the corpus modal. - `hero_token` (string): Canonical hero heading class signature (e.g. "text-display-xl" or "64"). When supplied, hero divergence is measured against this token rather than the corpus modal. - `pages` (array, required): At least 2 pages to compare. Each entry is {name, html}. ### `audit_video_playback` (~172 tokens) Render a page in headless Chromium and observe whether each