design-copier
Enables extraction of CSS styles from webpages and conversion to CSS format for use in web projects.
Provides tools to extract styles and convert them to React format, allowing reuse in React applications.
Allows applying extracted styles to React components using styled-components, generating ready-to-use component templates.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@design-copierCapture styles from https://example.com and convert to Tailwind"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
design-copier MCP Server
A webpage design extraction tool that captures and converts web designs for development
This is a TypeScript-based MCP server that implements a web design copying system. It allows you to:
Capture webpage styles and HTML structure
Extract and convert CSS to Tailwind classes
Apply extracted styles to different frontend frameworks
Features
Tools
designcopier_snapshot- Capture webpage or element stylesTakes a URL and optional CSS selector
Returns HTML and CSS styles from the target
designcopier_extract- Extract styles and convert to different formatsProcesses HTML and CSS content
Supports conversion to Tailwind classes
Can output in CSS, Tailwind, or React formats
designcopier_apply- Apply extracted styles to target frameworkTakes extracted styles and applies them to a component
Supports React (with styled-components)
Creates ready-to-use component templates
Related MCP server: imugi
Clone Repo and Development
Install dependencies:
npm installnpm run prepare , first time only or any custom changes Build the server:
npm run build , to make the build index.js fileFor development with auto-rebuild:
npm run watchInstallation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
VS-Code with Cline or Roo: Click top MCP Server icon, go to 'Installed' and at bottom of server list running, click 'Configure MCP Server' Add this to the config:
"design-copier": {
"timeout": 60,
"command": "node",
"args": [ "C:\\Users\\$ProfileUser$\\your-folder\\whatever folder\\design-copier\\build\\index.js"
],
"transportType": "stdio"
} Another example:
{
"mcpServers": {
"design-copier": {
"command": "node",
"args": [
"/path/to/design-copier/build/index.js"
],
"transportType": "stdio"
}
}
}Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
Available Tools
3 toolsdesigncopier_applyC
Apply extracted styles to target framework
| Name | Required | Description | Default |
|---|---|---|---|
| styles | Yes | Extracted styles | |
| targetFramework | Yes | Target framework | |
| componentName | Yes | Name for the generated component |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. It only says 'Apply extracted styles' without disclosing any side effects, permissions, or output behavior. Important for a code generation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely brief (one short sentence) but underspecified. Conciseness at the cost of completeness is not effective.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Missing context on output format, interaction with sibling tools, and practical usage steps. Schema covers params but not tool behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents each parameter. The description adds no additional meaning beyond what is in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Apply extracted styles to target framework' which clearly indicates the action (apply) and the resource (styles) and target. It distinguishes from sibling 'designcopier_extract' (which likely extracts) but does not differentiate from 'designcopier_snapshot'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance provided. Does not indicate when to use this tool versus alternatives, nor any prerequisites (e.g., need to extract styles first).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
designcopier_extractC
Extract styles and convert to different formats
| Name | Required | Description | Default |
|---|---|---|---|
| html | Yes | HTML content | |
| styles | Yes | CSS styles | |
| format | Yes | Output format |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as side effects, permissions, or output format. The tool's behavior beyond the schema is opaque.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that efficiently communicates the core functionality without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is insufficient. It does not explain the return value or behavior, leaving the agent with incomplete context for a tool with 3 parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all parameters. The description does not add additional meaning beyond the schema, such as explaining the enum values (css, tailwind, react). Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (extract and convert) and the resource (styles). It distinguishes from siblings like 'apply' and 'snapshot' through the verb 'extract'. However, it does not specify the source (HTML/CSS) explicitly, relying on the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. No conditions or exclusions are mentioned, leaving the agent without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
designcopier_snapshotC
Capture webpage or element styles
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to capture | |
| selector | No | Optional CSS selector for specific element |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description must carry full burden. Only states 'Capture', with no mention of side effects, authentication, rate limits, or what exactly is returned. Minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 5 words, perfectly concise and front-loaded. No unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite simple schema and no output schema, description fails to define what 'styles' entails (e.g., CSS properties, computed styles, or screenshots). Agent lacks critical context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already describes both parameters clearly (100% coverage). Description adds no extra meaning beyond schema, but does not repeat it. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Capture' and resource 'webpage or element styles', making the tool's function understandable. However, it does not differentiate from sibling tools like designcopier_extract, which may have overlapping purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance provided on when to use this tool versus alternatives or when not to use it. Lacks any contextual hints about suitability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
3 tool updates
v0.1.0- First observed
designcopier_apply - First observed
designcopier_extract - First observed
designcopier_snapshot
TDQS
Each tool has a distinct role in a clear pipeline: snapshot captures styles, extract converts them, and apply outputs to a target framework. No overlap in functionality.
All tool names follow a consistent pattern of 'designcopier_' prefix with a descriptive verb (snapshot, extract, apply) in snake_case.
3 tools are well-scoped for a focused design copying utility, covering the essential steps without bloat or insufficiency.
The pipeline is complete: capture (snapshot), transform (extract), and output (apply) cover the full workflow, with no missing steps for the stated purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
- miromiroOAuthapp.miromiro
Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code.
UI design from prompts, screenshots, and URLs for AI coding agents and theme tokens.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
AI-powered design and management for Webflow Sites
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConverts design screenshots into reusable Tailwind HTML components via MCP protocol, enabling any AI to extract and export individual UI elements.151MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI to capture, compare, and automatically patch frontend code against reference designs, achieving pixel-perfect fidelity without manual CSS tweaking.247MIT
- AlicenseNot gradedqualityDmaintenanceExtracts brand identity (colors, typography, spacing) from any website and generates HTML/CSS replicas or applies branding to templates.1MIT
- FlicenseNot gradedqualityDmaintenanceOne-click website design cloning with Puppeteer. Captures HTML, CSS, colors, fonts, and layout structured data for recreation.-
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/chipsxp/design-copier'
If you have feedback or need assistance with the MCP directory API, please join our Discord server