miromiro
Server Details
Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- SoraiaBarroso/miromiro-mcp
- GitHub Stars
- 0
- Server Listing
- miromiro-mcp
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Each tool targets a distinct asset type and the descriptions actively cross-reference alternatives ('Not for: icons and vector logos (use extract_svgs)'), which makes selection reliable. The only soft overlap is the brand/design-tokens/fonts triangle, where extract_brand, extract_design_tokens and extract_fonts all return typography and color data at different granularities; the descriptions differentiate them, but an agent could still hesitate on a vague request like 'tell me about this site's style'.
Ten of eleven tools use a uniform extract_<noun> pattern with nouns that name the resource precisely (assets, audio, svgs, videos, fonts, brand, code, page). The single list_site_pages follows the same verb_noun convention and is the one read-only listing operation, so the deviation is semantically meaningful rather than arbitrary.
Eleven tools is well within the ideal band and each maps to a genuine, non-redundant extraction target (raster, audio, video, SVG, Lottie, fonts, colors, tokens, section code, full page, page discovery). Nothing looks like filler, and the media-type splits are justified by very different parsing/rendering behavior.
The surface covers the full extraction lifecycle: discover pages (list_site_pages), extract one section (extract_code), extract a whole page (extract_page), plus every media and design-token category, with previews and downloads. Gaps are minor: there is no plain-text/markdown content extraction and no screenshot or metadata/SEO tool, though page copy is recoverable through extract_code.
Available Tools
11 toolsextract_assetsExtract imagesARead-onlyIdempotentInspect
Use when the user wants the images from a page - photos, illustrations, backgrounds, favicon, social image - as resolved URLs tagged by source (img, srcset, picture, CSS background, favicon, og). A URL that is itself an image file comes back as the single result (source file). Not for: icons and vector logos (use extract_svgs) or fonts (use extract_fonts). Returns up to 100 by default; pass limit (up to 200) for more.
Inputs: url (required), fresh, limit, render, +3 more. Returns: url, count, usage, images, +1 more
extract_audioExtract audioARead-onlyIdempotentInspect
Use when the user wants the audio files on a page: / files, og:audio, podcast enclosures and download links, each tagged by source. A URL that is itself an audio file comes back as the single result (source file). If a JavaScript player mounts the audio at runtime, call again with render=true (+5 credits). Returns up to 40 by default; pass limit (up to 200) for more.
Inputs: url (required), fresh, limit, render, +3 more. Returns: url, note, audio, count, +2 more
extract_brandExtract brand identityARead-onlyIdempotentInspect
Use when the user wants a site's brand: its colors, fonts, logo, theme or social links - 'what colors does stripe use', 'match this brand', 'build something in the style of X'. Returns role colors (primary, accent, background, text) as hex with human-readable names, the wider palette, fonts by role, logo candidates, social profiles, dark/light theme, and a 0-1 confidence score with signals explaining where the colors came from: read signals.explanation and tell the user whether they were declared by the site ('css-var'/'theme-color') or inferred from usage frequency ('usage', a guess) - never present inferred colors as the official palette. Not for: markup or layout (use extract_code) or the full token list (use extract_design_tokens).
Inputs: url (required), fresh, render, screenshot, +1 more. Returns: url, logo, next, fonts, +17 more
extract_codeExtract section as codeARead-onlyIdempotentInspect
Use when the user asks to rebuild, clone, copy, port, restyle or 'make it look like' part of a real website, or wants a site's section as Tailwind, HTML+CSS, React (JSX) or Vue - or as a file to import into a site builder: framework=elementor for an Elementor template (WordPress), framework=shopify for a Shopify theme section. Give it the URL and, when the user named a part of the page, section (hero, header, footer, pricing, features, testimonials, faq, cta) - never invent a CSS selector. With neither, it auto-detects the hero; every call also returns sections, each other extractable section with a label and a ready selector for a follow-up call. Returns a self-contained component with the page's real resolved styles (true colors, fonts, spacing, copy) plus the tokens and assets it uses, so you adapt real values instead of estimating from a screenshot. Not for: whole-page scraping, page text, or sites that need a login. Loads the page in a real browser and reads the styles, theme and images it actually shows, on every plan at no extra cost - no need to pass render=true. Large inline SVGs (logo walls, illustrations) come back as hosted files so the code stays small enough to use as-is (inline_svg=true keeps them inline). Ask for the format the user wants (framework=jsx for React, vue for Vue) instead of converting one into another. Build on code, never regenerate it: it is the section exactly as the site renders it. Then make it better to use where it can be: clear names for the component, props and variables; reusable small components with props instead of long repeated markup; hard-coded text and repeated items as props or a data array (jsx and vue already collapse repeated structures into .map()/v-for - keep that); shorter code by removing redundant wrappers, moving duplicated class lists into a shared component or constant, and dropping styles that do nothing (box-sizing: border-box is already Tailwind's default); and what the user asked for (their theme colors and fonts, removing parts). If the code is already clean, hand it over as it is. Every change must render the same: copy each className exactly as returned and never change a value (color, size, spacing, font) - retyping styles from memory loses the fidelity - and check your version against previewUrl. Elementor and Shopify files are imported as they are: do not edit them. Give the user downloadUrl, the code exactly as returned as a file in their format (.jsx, .vue, .html, .elementor.json, .liquid), and previewUrl, that code rendered as a page, to compare your version against. When rebuilding a whole page, extract each section and give them pagePreviewUrl: every section extracted so far, assembled in page order, also downloadable.
Inputs: url (required), name, fresh, theme, +7 more. Returns: css, url, code, hint, +17 more
extract_design_tokensExtract design tokensARead-onlyIdempotentInspect
Use when the user wants a site's complete token system - every color, font family, size, weight, spacing value, radius, shadow, line height, gradient and breakpoint with usage counts - or a paste-ready :root block (format='css'), tailwind.config (format='tailwind') or W3C Design Tokens file (format='dtcg'). Returns values and counts only, not layout or which element uses what: if the user asked to rebuild or clone a section, use extract_code, which returns the markup with the values in place. A site shipping light and dark themes returns the union of both (see colorSchemes) - pick colors by role, not by frequency. Not for: a short brand summary (use extract_brand). Lists trim to 60 per group; pass limit (up to 200) for more.
Inputs: url (required), fresh, limit, format, +4 more. Returns: format='json' returns the token lists below; format='css'|'tailwind' returns {…
extract_fontsExtract fontsARead-onlyIdempotentInspect
Use when the user asks which fonts a site uses or wants to match its typography: every @font-face file with family/weight/style/format, Google Fonts links and preloads, grouped per family in families (pass fields='families' for just that). On a type-foundry site the families served are demo cuts (subset, features stripped), flagged demo:true with a note - pass that on, they are not the usable typeface. Not for: colors (use extract_brand) or code (use extract_code). Lists trim to 50; pass limit (up to 200) for more.
Inputs: url (required), fresh, limit, fields, +4 more. Returns: url, note, count, fonts, +4 more
extract_lottieExtract Lottie animationsARead-onlyIdempotentInspect
Use when the user wants a site's Lottie or animation JSON files. Most Lotties are injected at runtime, so pass render=true (+5 credits) when the static call finds none. Returns up to 20 by default; pass limit (up to 200) for more.
Inputs: url (required), fresh, limit, render, +3 more. Returns: url, note, count, usage, +2 more
extract_pageExtract a whole page as codeARead-onlyIdempotentInspect
Use after list_site_pages, or when the user wants one complete page (not a single section) as code. Returns every section of the page top to bottom as code in the requested framework, plus pagePreviewUrl: the whole page assembled, with a Download HTML button. Flat credits per page (see usage.creditsSpent), whatever its length; a page already extracted in the last 24 hours is free. Paid plans only: on a free plan this returns an error explaining why - relay it and point the user to extract_code for single sections. Call it once per page the user picked, one at a time, and tell them how many are left as you go. If complete is false, call again with the same url: the done sections come from cache and the page is not charged again. Build on each section's code the same way as extract_code's (never regenerate it), and give the user pagePreviewUrl for every page.
Inputs: url (required), theme, framework. Returns: url, usage, failed, complete, +5 more
extract_svgsExtract SVGsARead-onlyIdempotentInspect
Use when the user wants a site's icons or vector logos: inline SVGs as paste-ready markup plus external .svg file URLs. Not for: raster images (use extract_assets). Returns 20 by default with long markup trimmed; pass limit (up to 200) for more and full_output=true for complete SVG code.
Inputs: url (required), fresh, limit, render, +3 more. Returns: url, svgs, count, usage, +1 more
extract_videosExtract videosARead-onlyIdempotentInspect
Use when the user wants the videos on a page: / files, og:video, YouTube/Vimeo/Wistia/Loom embeds, direct video links and the JSON-LD VideoObject a page declares (source: "structured-data", how news sites describe a JS-mounted video), each tagged by source with a poster when declared. source: "embed" is a player page, not a downloadable file; a URL that is itself a video file comes back as the single result (source file). A YouTube, Vimeo, TikTok, Dailymotion or Loom video URL is answered from the URL alone with its player embed (source: "platform", no fetch, never pass render for these) - tell the user the file itself cannot be downloaded through MiroMiro. When any other page loads a JS player and declares nothing else, the hint names the player: call again with render=true (+5 credits) then. Returns up to 40 by default; pass limit (up to 200) for more.
Inputs: url (required), fresh, limit, render, +3 more. Returns: url, note, count, usage, +2 more
list_site_pagesList a website's pagesARead-onlyIdempotentInspect
Use when the user wants a whole website (or several of its pages) as code, or asks which pages a site has. Free on every plan (0 credits). Returns every page found (from the sitemap, else the homepage links), split into pages with their own layout (home, pricing, about...) and templates: groups of pages that share one layout (blog post x62, product x24) with example URLs - extracting one example gives that layout. suggested covers every layout once. Show the user the list and ask which pages they want before extracting anything: say how many pages and templates there are and what extract_page costs (creditsPerPage credits per page). Never extract every page of a big site unprompted. Then call extract_page once per chosen page. If the result has premium, the user's plan does not include whole-site extraction: tell them premium.reason and give them premium.upgradeUrl; single sections still work with extract_code.
Inputs: url (required), response_format. Returns: url, pages, usage, source, +7 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
See the rendered web: design tokens, fonts, animation timings, WebGL shaders and 3D from any URL.
Real HTML, styles, measurements and brand tokens from any live site, for coding agents.
DESIGN.md, clone prompts, HTML, screenshots, assets, fonts, colors and tech stack of any website.
Logo, colors, typefaces, tone of voice and CSS theme of any brand, read from its own website.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceExtracts brand identity (colors, typography, spacing) from any website and generates HTML/CSS replicas or applies branding to templates.1MIT
- AlicenseAqualityBmaintenanceSearches design platforms for UI references and extracts design tokens such as colors, typography, spacing, and shadows from live websites.5MIT
- AlicenseNot gradedqualityAmaintenanceExtract design tokens, colors, typography, spacing and components from any live website, and compute design drift against an approved baseline. Exports DESIGN.md, DTCG, Tailwind and shadcn.8,776 npm3,943MIT
- AlicenseAqualityCmaintenanceAnalyzes and extracts design tokens, assets, and layout from live websites to enable AI clients to faithfully replicate them, with tools for screenshotting, component inspection, and pixel-diff verification.1429 npm4MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.