Carbon MCP provides tools to explore Carbon Design System components, tokens, and icons, answer documentation questions, and generate consistent UI code.
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
- !No standard license detected
git clone https://github.com/carbon-design-system/carbon-mcp{
"mcpServers": {
"carbon-mcp": {
"command": "node",
"args": ["/path/to/carbon-mcp/dist/index.js"]
}
}
}MCP Servers overview
# Carbon MCP - issue tracking This repository serves as the central place to report issues and request new features for Carbon MCP. Visit the Carbon MCP website to get started: - [Overview](https://www.carbondesignsystem.com/getting-started/carbon-mcp/overview): Carbon MCP overview and key benefits - [Concepts](https://www.carbondesignsystem.com/getting-started/carbon-mcp/concepts): Details on the Carbon MCP tools and content coverage - [Onboarding and setup](https://www.carbondesignsystem.com/getting-started/carbon-mcp/onboarding-and-setup): Getting authentication credentials and connecting to common MCP clients - [Prompts](https://www.carbondesignsystem.com/getting-started/carbon-mcp/prompts): Prompting guidance and best practices - [Token conservation](https://www.carbondesignsystem.com/getting-started/carbon-mcp/token-conservation): Keeps AI workflows fast and cost-efficient by reducing unnecessary context and responses without losing quality <br /> <img src="public/carbon-mcp.svg" alt="Carbon MCP GitHub banner showing tagline about AI expertise in Carbon" width="650" /> ## What is MCP? MCP (Model Context Protocol) is an open-source standard that enables AI agents or AI applications to securely connect with external tools, data sources, and workflows through a unified integration layer. ## Carbon MCP ➤ **Carbon MCP makes any agentic AI application an instant expert in the Carbon Design System, enabling teams to deliver consistent, high‑quality user experiences with greater speed.** - _Instant AI Access to Carbon Design Standards_: Carbon MCP lets AI applications or agents directly query the Carbon design system for pertinent context (e.g. colors, typography, component source, usage guidelines, etc.). - _Smarter Code Generation_: Code examples and documentation exposed via Carbon MCP allows AI tools to generate high-fidelity Carbon UI code that conforms to design and development best practices. - _Improved Consistency_: AI tools that integrate Carbon MCP gives designers, developers, and PMs consistent answers and examples from a shared source of truth, helping reduce drift and rework. ## Summary of Carbon MCP Coverage Carbon MCP continues to evolve. Current coverage is provided below: #### ✅ `@carbon/react` - Code examples and documentation - Example: Button, Tabs, TextInput, etc. - Multiple variants per component - Complete props and imports #### ✅ `@carbon/web-components` - Code examples and documentation - Example: button, tabs, text-input, etc. - Multiple variants per component - Complete props and imports #### ✅ Carbon for IBM Products - Code examples and documentation - Example: Tearsheets, PageHeader, etc. - Multiple variants per component - Complete props and imports #### ✅ Carbon Icons and Pictograms - Code examples and documentation - Example: Settings, User, UserAvatarFilled, etc. - Usage #### ✅ `@carbon/ai-chat` - Code examples and documentation - Example: basic, custom-element, history, etc. - Full code examples - Complete props and imports #### ✅ `@carbon/charts` - Chart type descriptions - Links to demos - Full code examples - Complete props and imports #### ✅ `@carbon-labs/*` - Code examples and documentation for preview candidates - React - AnimatedHeader, Processing, Resizer, UIShell, and What's New - Multiple variants per component - Complete props and imports #### ⛔ Support coming soon! - Carbon TanStack - Carbon Patterns
What people ask about carbon-mcp
What is carbon-design-system/carbon-mcp?
+
carbon-design-system/carbon-mcp is mcp servers for the Claude AI ecosystem. Carbon MCP provides tools to explore Carbon Design System components, tokens, and icons, answer documentation questions, and generate consistent UI code. It has 37 GitHub stars and its last recorded update is dated 2026-10-09.
How do I install carbon-mcp?
+
You can install carbon-mcp by cloning the repository (https://github.com/carbon-design-system/carbon-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is carbon-design-system/carbon-mcp safe to use?
+
Our security agent has analyzed carbon-design-system/carbon-mcp and assigned a Trust Score of 62/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains carbon-design-system/carbon-mcp?
+
carbon-design-system/carbon-mcp is maintained by carbon-design-system. The last recorded GitHub activity is dated 2026-10-09, with 1 open issues.
Are there alternatives to carbon-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy carbon-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/carbon-design-system-carbon-mcp)<a href="https://claudewave.com/repo/carbon-design-system-carbon-mcp"><img src="https://claudewave.com/api/badge/carbon-design-system-carbon-mcp" alt="Featured on ClaudeWave: carbon-design-system/carbon-mcp" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
The fastest path to AI-powered full stack observability, even for lean teams.