What clients does Design Systems MCP Server support?
It works with any MCP-capable client, including Claude Desktop, Claude Code (CLI), Cursor IDE, Cline (VSCode), Continue (VSCode), Zed Editor, and generic MCP clients.
@southleft
基本情報
I'm your specialized design systems assistant. Ask me about components, tokens, patterns, and best practices.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"design-systems": {
"command": "npx",
"args": [
"mcp-remote",
"https://design-systems-mcp.southleft-llc.workers.dev/mcp"
]
}
}
}Search through design system knowledge base entries by query, category, or tags
Search through specific content chunks for detailed information
Browse all entries in a specific category
Get a list of all available tags in the knowledge base
List all entries carrying a specific tag (use get_all_tags to discover tags)
An AI-powered Model Context Protocol (MCP) server providing intelligent access to authoritative design systems knowledge. It is powered by Supabase vector search with 200+ curated entries including W3C standards, WCAG guidelines, and design system best practices. It is intended for developers, designers, and accessibility specialists who need quick, accurate answers about design systems.
Connect any MCP-capable client (e.g., Claude Desktop, Cursor, Windsurf) to the public endpoint https://design-systems-mcp.southleft.com/mcp with zero setup. For local development, clone the repository, run npm install, configure environment variables, and start with npm run dev. The server exposes four MCP tools: search_design_knowledge, search_chunks, browse_by_category, and get_all_tags.
It works with any MCP-capable client, including Claude Desktop, Claude Code (CLI), Cursor IDE, Cline (VSCode), Continue (VSCode), Zed Editor, and generic MCP clients.
You can ingest web content via `npm run ingest:url <URL>`, bulk ingest from CSV with `npm run ingest:csv <file>`, ingest PDFs with `npm run ingest:pdf <file>`, or crawl entire websites with `npm run crawl:website <URL>`. After ingestion, run `npm run ingest:vectors` to generate embeddings.
Yes. The live demo is at `https://design-systems-mcp.southleft.com/`. It includes an AI chat interface that streams responses via SSE and a landing page with MCP endpoint details.
Four tools: `search_design_knowledge` (semantic search across the knowledge base), `search_chunks` (find specific content in chunks), `browse_by_category` (browse content by categories like components, tokens, patterns), and `get_all_tags` (list all content tags for filtering).
The public MCP endpoint is available without authentication. Local development requires setting environment variables (e.g., Supabase and OpenAI keys) in a `.dev.vars` file.

Build and run AI product photography workflows from your AI assistant: on-model shots, catalog images, prints and edits, with results returned in chat.
Photo mosaic maker and AI photo collage maker: turn your own photos into a photo mosaic - one picture made of hundreds of your photos - or into a heart, number or word photo collage in seconds. No sign-in or API key need

Built by movie lovers, for movie lovers and their assistants. SceneF puts every screen in California and Hawaii on one board — 33 regions, from San Francisco's single-screen neighborhood houses and nightly repertory cale

Make AI-drawn video from chat. Claude, Cursor or Claude Code plans the film, the model draws every frame in code at 30 fps, and you edit it on a timeline with narration, music and sound effects.

Generate images, video, audio and short films with 140+ AI models from any MCP client. PixelDojo picks the right model (Flux, Seedream, Seedance, Veo, Kling, WAN, Nano Banana, GPT Image), renders it and returns download
コメント