miromiro-mcp

MCP server for the MiroMiro design-extraction API. Give your AI agent the real design of any live website - brand colors, fonts, design tokens, SVGs, images, Lottie animations, and paste-ready component code - so it builds from actual values instead of guessing from a screenshot.

Works with Claude (web, desktop, Claude Code), ChatGPT, Cursor, Windsurf, Codex, and any MCP client.

Claude Code plugin

Install as a plugin to get the tools plus three skills that teach Claude when to reach for each one (clone-section, match-brand, extract-assets):

claude plugin marketplace add anthropics/claude-plugins-community
claude plugin install miromiro@claude-community

The plugin uses the remote server, so there is nothing to install and no key to paste - on first use it opens a one-click MiroMiro sign-in that links a free account (300 credits/month, no card).

Quick start: remote server (nothing to install)

A hosted server lives at:

https://miromiro.app/mcp

Paste that URL into any client that accepts a remote MCP server. On first use it opens a one-click MiroMiro sign-in that links a free account (300 credits/month, no card).

• Claude (web or desktop): Settings → Connectors → Add custom connector → paste the URL. Or use the one-click install.
• ChatGPT: Settings → Security and login → enable Developer mode, then add the URL as a connector (authentication: OAuth).
• Cursor (remote): add { "mcpServers": { "miromiro": { "url": "https://miromiro.app/mcp" } } } to ~/.cursor/mcp.json.
• Raw API key instead of OAuth: append ?access_key=mm_live_... to the URL, or send it as an Authorization: Bearer header.

Local server (npm)

Prefer a local stdio process with the key in an env var? Get a free key at miromiro.app/api/dashboard, then:

Cursor (~/.cursor/mcp.json) / Windsurf (Settings → MCP):

{
  "mcpServers": {
    "miromiro": {
      "command": "npx",
      "args": ["-y", "miromiro-mcp"],
      "env": { "MIROMIRO_API_KEY": "mm_live_your_key" }
    }
  }
}

Claude Code (run in your terminal, not inside a claude session):

claude mcp add miromiro -s user \
  --env MIROMIRO_API_KEY=mm_live_your_key \
  -- npx -y miromiro-mcp

Tools

All tools are read-only and retry-safe. Identical calls within 24 hours are served from cache for free, and failed calls are never billed.

Asking for a part of the page by name

extract_code takes section - one of hero, header, footer, pricing, features, testimonials, faq, cta - so the agent never has to invent a CSS selector for a page it cannot see. Every result also lists the page's other sections with ready selectors for follow-up calls. A selector or section that matches nothing falls back to the hero with a note saying what the page does have, instead of a dead-end 404.

Prompts (slash commands)

The server exposes three MCP prompts, which clients surface before the first call - Claude Code as /mcp__miromiro__clone_section, /mcp__miromiro__brand_kit and /mcp__miromiro__design_tokens, VS Code as /miromiro.<name>, Cursor in its prompt menu:

Controlling output size (remote server)

Remote results are trimmed by default so a big page cannot flood the chat context, and every trimmed response says exactly what was dropped. Two optional arguments loosen it per call:

• response_format: 'concise' | 'detailed' - the one-word knob: concise keeps lists to 10 entries for a chat answer, detailed returns everything the tool has
• limit (up to 200) - raise the item cap: "give me 80 SVGs, not 20"
• full_output: true - complete long strings, like entire inline SVG markup

Generated code is never trimmed. Results stop at roughly 20k tokens (25k for extract_code) so they fit the tool-result cap of Claude Code, Claude Desktop and Cursor, and the truncation_note says how many tokens were cut and which argument brings them back.

The REST API and this local npm server always return everything untrimmed, so limit and full_output apply to the remote server only. Every tool on both servers accepts render: true (paid API plans and credit packs only - a free account gets 402 render_requires_plan and nothing runs, except when the site itself refuses the request: see Notes), plus two more shared arguments:

• fresh: true - skip the 24-hour cache and re-extract the live page (charged normally); use when the site just changed
• screenshot: true (requires render: true) - the result gains a screenshot field: a public URL of a 1440x900 capture of the page, live for 7 days, at no extra credits - show it to the user to verify an extraction. Pass 'full' instead of true for the entire page height.

Examples

"Rebuild stripe.com's pricing section in React"

The agent calls extract_code with the URL, gets the section's real markup, colors, fonts, and spacing, and adapts actual values instead of guessing.

Extraction returns a page's light styles by default, so a site you know as dark comes back light unless you ask otherwise:

"Rebuild linear.app's pricing card in its dark theme"

The agent passes theme: "dark" and the page's prefers-color-scheme: dark rules and custom properties become the component itself. Every result also carries a theme field saying which one you actually got. Sites that switch themes with a JavaScript class toggle cannot be selected this way - you get the page default plus a hint saying so.

"Build a dashboard in the style of linear.app"

The agent calls extract_brand and extract_design_tokens, gets Linear's real colors, fonts, and spacing scale, and builds to match.

"What fonts does apple.com use?"

The agent calls extract_fonts and returns every family with its font file URLs and weights.

Notes

• The API reads static HTML and resolves the full CSS cascade by default, so a fully client-rendered app may return little for images, video, audio and Lottie (tokens, fonts, brand, and code come from CSS and are unaffected). Pass render: true on any remote-server tool to run the page in a real browser first so its JavaScript executes (+5 credits). Rendering is included in the paid API plans and credit packs, not in the free account: a free account gets 402 render_requires_plan before anything runs or is charged.
• One exception, and it needs no flag: when the SITE refuses a free account's plain request (401, 403 or 406 - publishers commonly turn away datacenter IPs even for a public page), the server retries that call in a real browser automatically and free, a few times a month. The result then carries usage.renderRescue (a sentence to read to the user) and usage.renderRescuesLeft. So on a free account, do not treat a 401/403/406 as "this site cannot be extracted" until those are used up.
• Every result carries usage with the credits left this month. If the account holds a credit pack (one-off credits that never expire, bought at https://miromiro.app/api/pricing), usage.packCredits is the pack balance left; packs are drawn after the monthly credits, so a free account with a pack keeps working past its 300 credits.
• Respect the sites you extract from: check their terms before reusing assets commercially.

Links

API docs · Playground (no account) · Pricing · Changelog · Connect page

MIT © MiroMiro