MCP server for extracting design systems from live websites, including design tokens, regions, components, contrast data, Tailwind themes, Figma variables, and prompt packs.
designlang uses Playwright to crawl live pages and can capture DOM-derived styles, responsive behavior, interaction states, screenshots, and accessibility findings., Authenticated extraction options can use cookies, cookie files, headers, and custom user agents, so never pass production session cookies or credentials unless approved., Generated outputs may include design tokens, Tailwind config, shadcn variables, Figma variables, component anatomy, prompts, screenshots, reports, and cloned starter code., Commands such as apply, clone, sync, drift, visual-diff, and MCP extraction can read live websites and write files in the configured output or project directory., Review extracted prompt packs and generated code before using them in another agent workflow or committing them.
Privacy notes
URLs, page content, DOM text, CSS, screenshots, fonts, images, design tokens, cookies, headers, prompts, tool arguments, reports, and generated files may be visible to the MCP client and model provider., Authenticated or internal sites can expose product plans, unreleased UI, customer data, analytics identifiers, private brand assets, and implementation details., Output directories can retain extracted website data after the MCP session ends., Avoid running the server against private, paid, internal, or authenticated properties without legal and security approval.
Author
Manavarya09
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens.
5 areas
SafetyGeneraldesignlang uses Playwright to crawl live pages and can capture DOM-derived styles, responsive behavior, interaction states, screenshots, and accessibility findings.
SafetyCredentials & tokensAuthenticated extraction options can use cookies, cookie files, headers, and custom user agents, so never pass production session cookies or credentials unless approved.
SafetyCredentials & tokensGenerated outputs may include design tokens, Tailwind config, shadcn variables, Figma variables, component anatomy, prompts, screenshots, reports, and cloned starter code.
SafetyLocal filesCommands such as apply, clone, sync, drift, visual-diff, and MCP extraction can read live websites and write files in the configured output or project directory.
SafetyGeneralReview extracted prompt packs and generated code before using them in another agent workflow or committing them.
PrivacyCredentials & tokensURLs, page content, DOM text, CSS, screenshots, fonts, images, design tokens, cookies, headers, prompts, tool arguments, reports, and generated files may be visible to the MCP client and model provider.
PrivacyTelemetryAuthenticated or internal sites can expose product plans, unreleased UI, customer data, analytics identifiers, private brand assets, and implementation details.
PrivacyCredentials & tokensOutput directories can retain extracted website data after the MCP session ends.
PrivacyExecution & processesAvoid running the server against private, paid, internal, or authenticated properties without legal and security approval.
Safety notes
designlang uses Playwright to crawl live pages and can capture DOM-derived styles, responsive behavior, interaction states, screenshots, and accessibility findings.
Authenticated extraction options can use cookies, cookie files, headers, and custom user agents, so never pass production session cookies or credentials unless approved.
Generated outputs may include design tokens, Tailwind config, shadcn variables, Figma variables, component anatomy, prompts, screenshots, reports, and cloned starter code.
Commands such as apply, clone, sync, drift, visual-diff, and MCP extraction can read live websites and write files in the configured output or project directory.
Review extracted prompt packs and generated code before using them in another agent workflow or committing them.
Privacy notes
URLs, page content, DOM text, CSS, screenshots, fonts, images, design tokens, cookies, headers, prompts, tool arguments, reports, and generated files may be visible to the MCP client and model provider.
Authenticated or internal sites can expose product plans, unreleased UI, customer data, analytics identifiers, private brand assets, and implementation details.
Output directories can retain extracted website data after the MCP session ends.
Avoid running the server against private, paid, internal, or authenticated properties without legal and security approval.
Prerequisites
Node.js 20 or newer available to the MCP client runtime.
Network access to the websites you plan to extract.
Permission to crawl and analyze the target sites.
Playwright or Chromium installation behavior reviewed for the local environment.
Output directory reviewed before writing extracted tokens, screenshots, reports, and generated project files.
designlang is an MCP server and CLI for extracting design systems from live
websites. It can expose design tokens, semantic regions, components, contrast
pairs, Tailwind themes, Figma variables, prompt packs, screenshots, and design
reports to Claude-compatible MCP clients.
The upstream README documents designlang mcp as the stdio MCP server command.
The package metadata exposes the designlang binary, and the MCP registry docs
show the npx -y designlang mcp configuration.
These sources were reviewed on 2026-06-05. Prefer the live repository,
README, package metadata, security policy, MCP registry notes, and NPM registry
metadata for current command names, Node requirements, extraction behavior,
supported outputs, and safety guidance.
Ask Claude to extract design tokens from a public website before building a matching UI.
Generate Tailwind, shadcn, CSS variable, or Figma variable handoff files.
Compare two sites and explain design differences.
Review WCAG contrast findings and remediation suggestions.
Capture component anatomy, responsive behavior, motion patterns, and brand voice.
Create prompt packs for frontend generation workflows.
Safety and Privacy
designlang crawls live pages with Playwright and can write detailed outputs.
Treat extraction results as a copy of website content and design intelligence,
especially when using authenticated pages, private staging sites, cookie files,
custom headers, or internal URLs.
Review output directories before sharing or committing generated files. Screenshots,
tokens, prompts, Figma variables, Tailwind configs, reports, and clone starters
may reveal proprietary design systems, unpublished pages, analytics identifiers,
or user-visible data from the crawled page.
Duplicate Check
No Manavarya09/design-extract entry, designlang package entry, or matching
source URL was found in content/mcp.
Show that designlang MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/designlang-mcp-server)
How it compares
designlang MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
MCP server for extracting design systems from live websites, including design tokens, regions, components, contrast data, Tailwind themes, Figma variables, and prompt packs.
Figma MCP bridge that connects Claude Code, Cursor, and other agents to a Figma plugin through WebSocket channels so they can read designs and modify nodes, text, layouts, styles, annotations, and components.
MCP server and Agent Skill from better-auth for searching, recommending, retrieving, batching, and syncing Iconify-powered SVG icons from 200,000+ icons across 150+ collections.
✓designlang uses Playwright to crawl live pages and can capture DOM-derived styles, responsive behavior, interaction states, screenshots, and accessibility findings.
Authenticated extraction options can use cookies, cookie files, headers, and custom user agents, so never pass production session cookies or credentials unless approved.
Generated outputs may include design tokens, Tailwind config, shadcn variables, Figma variables, component anatomy, prompts, screenshots, reports, and cloned starter code.
Commands such as apply, clone, sync, drift, visual-diff, and MCP extraction can read live websites and write files in the configured output or project directory.
Review extracted prompt packs and generated code before using them in another agent workflow or committing them.
✓TalkToFigma can read and modify Figma documents, selected nodes, text content, annotations, auto-layout settings, fills, strokes, component instances, prototype reactions, and exported node images.
Agents can create, move, resize, clone, and delete nodes, so use a duplicate file or branch-like design workflow before broad edits.
Always join the intended WebSocket channel and verify the active Figma document before running write tools.
Review batch text replacements, component override propagation, annotation conversion, and connector generation before sharing or handing off design files.
Keep the WebSocket bridge local or otherwise protected so untrusted clients cannot attach to an active Figma session.
✓AgentQL MCP exposes one tool, `extract-web-data`, that sends a target URL and natural-language extraction prompt to the AgentQL API.
The tool is intended for public webpages; do not use it to bypass access controls, scrape private pages, evade paywalls, or extract data where automated collection is prohibited.
Web extraction can still trigger target-site rate limits, legal restrictions, robots guidance, or terms-of-service concerns.
The source implementation uses AgentQL's query-data endpoint with fast mode, no screenshot capture, no scroll-to-bottom behavior, and no local browser cookies.
Treat extracted output as untrusted web data that may include errors, stale content, ads, tracking text, or prompt-injection attempts.
✓Better Icons can write icons into a project file through `sync_icon`; review the target path, component name, framework, and diff before committing generated code.
Icon output can include raw SVG, JSX/component usage, URLs, or generated project code. Review SVG attributes and generated code before use in production UI.
Learned preferences and recent icons can influence future recommendations; clear preferences when switching projects or style systems.
Batch retrieval can add many icons quickly. Keep requested sets bounded and avoid mixing unrelated icon styles in a shared design system.
Privacy notes
✓URLs, page content, DOM text, CSS, screenshots, fonts, images, design tokens, cookies, headers, prompts, tool arguments, reports, and generated files may be visible to the MCP client and model provider.
Authenticated or internal sites can expose product plans, unreleased UI, customer data, analytics identifiers, private brand assets, and implementation details.
Output directories can retain extracted website data after the MCP session ends.
Avoid running the server against private, paid, internal, or authenticated properties without legal and security approval.
✓Figma document structure, node names, selected content, annotations, component metadata, local styles, exported images, text content, and prototype information may be exposed to the MCP client and model.
Design files often contain unreleased product UI, customer data in mockups, brand assets, internal names, tokens, pricing, screenshots, or partner/client IP.
Exported images can include visual details that are more sensitive than node metadata alone.
Channel names, WebSocket messages, local logs, and MCP prompts may reveal active file context and design intent.
✓Target URLs, extraction prompts, API key-authenticated requests, and extracted structured data are sent to AgentQL's API.
Extracted data can include personal data, copyrighted content, customer information, job postings, prices, social content, or other third-party material.
AGENTQL_API_KEY should stay out of prompts, issues, logs, screenshots, and committed configuration files.
Claude transcripts and downstream reports may retain extracted data, so avoid collecting information that is not approved for the model session.
✓Icon search queries, selected icon IDs, preferred collections, recent icons, target icon file paths, framework names, and generated SVG/component code may be visible to the MCP client and model provider.
`sync_icon` can expose local project structure and icon-file conventions to the agent.
Avoid sending private product names, unreleased feature labels, customer-specific UI terms, or proprietary design-system names in icon search prompts when that context is sensitive.
Prerequisites
Node.js 20 or newer available to the MCP client runtime.
Network access to the websites you plan to extract.
Permission to crawl and analyze the target sites.
Playwright or Chromium installation behavior reviewed for the local environment.
Bun installed through a trusted installation path.
Figma desktop or browser session with access to the design file you are authorized to inspect or modify.
The TalkToFigma Figma plugin installed from the documented upstream path or linked locally from the repository.
WebSocket bridge running with `bun socket`.
Node.js and npx available to the MCP client runtime.
AgentQL API key from the AgentQL developer portal.
Approved list of public webpages or domains Claude may query.
Review of target site terms, robots guidance, rate limits, and data-use rules before extraction.
Node.js 18 or newer for the `better-icons` npm package.
An MCP client such as Claude Code, Cursor, OpenCode, Windsurf, VS Code Copilot, Google Antigravity, or another stdio-capable MCP host.
Network access to Iconify icon data and package registry downloads.
For project sync, an approved target icons file and framework choice such as React, Vue, Svelte, Solid, or raw SVG.
Install
npx -y designlang mcp
bunx cursor-talk-to-figma-mcp@latest
npx -y agentql-mcp
claude mcp add better-icons -- npx -y better-icons