.github

Created By
agentiencea year ago
A Model Context Protocol (MCP) server that provides comprehensive information about React design systems, along with code generation capabilities for common UI patterns. Currently supports AWS Cloudscape Design System, with plans to add support for Material UI, Chakra UI, Ant Design, and other popular React design systems in the future.
Overview

What is React Design Systems?

React Design Systems is a Model Context Protocol (MCP) server that provides comprehensive information about React design systems, focusing on the AWS Cloudscape Design System. It includes code generation capabilities for common UI patterns and aims to support additional popular design systems in the future.

How to use React Design Systems?

To use React Design Systems, install it via npm as a dependency or globally. You can then run the server directly or configure it with Claude Desktop for automatic launching.

Key features of React Design Systems?

  • Comprehensive component information and search capabilities.
  • Code generation for components and UI patterns.
  • Advanced functionality including usage guidelines, events, and functions exploration.
  • Support for Docker deployment.

Use cases of React Design Systems?

  1. Searching for and retrieving detailed information about UI components.
  2. Generating code snippets for UI components and layouts.
  3. Accessing usage guidelines and best practices for design systems.

FAQ from React Design Systems?

  • What design systems are currently supported?

Currently, it supports the AWS Cloudscape Design System, with plans to add Material UI, Chakra UI, Ant Design, and others.

  • Is there a CLI tool available?

Yes, you can install it globally and use it as a CLI tool.

  • Can I deploy it using Docker?

Yes, detailed instructions for Docker deployment are provided in the documentation.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
agentience
Star
1
Language
D
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

10 hours ago