miromiro-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y miromiro-mcp@0.11.1
Installing a package runs its code. Use a sandbox for anything you have not read.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
1 tool with commands in capitals or very long text
- Very long description in
extract_code:3000 characters or more
Common and usually harmless: it is how many makers stress how a tool should be used.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
extract_code url, section, selector, framework, name, theme, inline_svg, render, fresh, screenshot
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. For jsx/vue, repeated structures collapse into a data array rendered with .map()/v-for; ::before/::after come back as real elements; @keyframes ship in the css field. The `theme` field says which theme the code actually is - sites with a prefers-color-scheme dark variant return the light branch unless you pass theme='dark'; say which you returned. 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 <img> 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
extract_brand url, render, fresh, screenshot
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).extract_design_tokens url, format, render, fresh, screenshot
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', for Style Dictionary / Figma variables). 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, and use extract_code with theme=dark for one theme on its own. Not for: a short brand summary (use extract_brand).
extract_assets url, render, fresh, screenshot
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 direct image-file URL comes back as the single result (source file). Not for: icons and vector logos (use extract_svgs) or fonts (use extract_fonts). If images are mounted by JavaScript, call again with render=true (+5 credits).
extract_svgs url, render, fresh, screenshot
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). If icons are mounted by JavaScript, call again with render=true (+5 credits).
4 more tools
extract_fonts url, fields, render, fresh, screenshot
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).
extract_lottie url, render, fresh, screenshot
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.
extract_videos url, render, fresh, screenshot
Use when the user wants the videos on a page: <video>/<source> files, og:video, YouTube/Vimeo/Wistia/Loom embeds and direct video links, each tagged by source with a poster when declared. `source: "embed"` is a player page, not a downloadable file; a direct video-file URL 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. Most other players mount with JavaScript: if the result is thin or empty, call again with render=true (+5 credits).
extract_audio url, render, fresh, screenshot
Use when the user wants the audio files on a page: <audio>/<source> files, og:audio, podcast enclosures and download links, each tagged by source; a direct audio-file URL comes back as the single result (source file). If a JavaScript player mounts the audio at runtime, call again with render=true (+5 credits).
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=18 |
| Source | github.com/SoraiaBarroso/miromiro-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-40UohXanSnBy2W0l5fjYcUxlQmQfUrlpa8DbRDCVU2CcZkq5n7yV4itIV6fxrORt98bI3HV56/eG4YUvNp1jrA== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/miromiro-mcp)
New version out? Ask for a fresh report.