Next.js + React + Tailwind Assistant
Provides comprehensive documentation search for Next.js 15+ and Tailwind CSS 3+, along with 27 production-ready Catalyst UI components and 13 design patterns for building modern web applications.
README
Next.js + React + Tailwind Assistant MCP Server
Your comprehensive AI companion for building modern Next.js applications with React and Tailwind CSS.
Features
📚 Complete Documentation
- Next.js 15+: App Router, Server Components, Server Actions, routing, data fetching
- Tailwind CSS 3+: All utility classes, responsive design, dark mode, customization
- Smart Search: Targeted results without overwhelming context
🎨 27 Catalyst UI Components
- Production-ready TypeScript React components
- Built with Tailwind CSS and Headless UI
- Fully accessible, responsive, and customizable
- Categories: forms, navigation, layout, feedback, data display
✨ 13 Design Patterns
Abstracted from 11 professional Next.js templates:
Visual Effects: Gradients, glows, animations, bento grids, decorative SVGs Component Library: Buttons, cards, badges, inputs, avatars, alerts, tooltips Color Systems: 8 palette strategies (Professional, SaaS, Bold, Minimal, Semantic, Dark Mode) Typography: Font systems, type scales, responsive patterns Layouts: App headers, auth pages, sidebars, overlay navigation Pages: Hero sections, pricing tables, blog layouts
All patterns include accessibility, performance, and dark mode support.
Installation
Via Smithery
npx @smithery/cli install @username/nextjs-react-tailwind-assistant --client claude
Manual Installation
- Clone the repository:
git clone https://github.com/CaullenOmdahl/Nextjs-React-Tailwind-Assistant.git
cd Nextjs-React-Tailwind-Assistant
- Install dependencies:
npm install
- Build the server:
npm run build
This will:
- Build the MCP server using Smithery CLI →
.smithery/index.cjs(1.67 MB) - Copy the content directory →
.smithery/content/(5.3 MB)
Development
npm run dev # Start development server with hot reload
npm run inspector # Launch MCP inspector for testing
npm run build # Build production bundle
npm run watch # TypeScript watch mode
Available Tools
search_nextjs_docs- Search Next.js documentationsearch_tailwind_docs- Search Tailwind CSS utilities and conceptsget_nextjs_full_docs- Complete Next.js documentation (large)get_tailwind_full_docs- Complete Tailwind documentation (large)get_catalyst_component- Retrieve production-ready componentslist_catalyst_components- Browse available componentslist_patterns- Browse design patternsget_pattern- Get detailed pattern implementations
Content Structure
content/
├── components/
│ └── catalyst/ # 27 TypeScript React components
├── docs/
│ ├── nextjs/ # Complete Next.js 15+ docs (2.9 MB)
│ └── tailwind/ # Complete Tailwind CSS docs (2.1 MB)
├── patterns/
│ ├── features/ # 6 feature patterns
│ ├── layouts/ # 4 layout patterns
│ └── pages/ # 3 page patterns
└── content-summary.json # Catalog of all content
Deployment to Smithery
Important: Content Directory Deployment
The server requires the content/ directory (5.3 MB) to be available at runtime. Smithery deploys from your GitHub repository and includes files listed in package.json "files" array.
Deployment Process:
- Ensure content is committed to git:
git add content/
git commit -m "Add documentation and pattern content"
- Push to GitHub:
git push origin main
- Deploy to Smithery:
- Smithery clones your repository
- Runs
npm install - Runs
npm run build(which copies content to.smithery/content/) - Deploys the server
Note: The server uses process.cwd() + '/content' to locate files. When deployed to Smithery, the content directory from your repository should be available in the working directory.
Troubleshooting Deployment
If you get a 500 error on Smithery:
- Verify content is in repository:
git ls-files content/ | wc -l # Should show files
du -sh content/ # Should show ~5.3M
- Check package.json "files" array includes "content":
"files": ["dist", "content", "icon.png", "icon.svg"]
- Ensure build copies content:
npm run build
ls -la .smithery/content/ # Should show content directory
- Test locally:
cd .smithery && node index.cjs
# Should start without errors
Architecture
Module System
- ES Modules only (
"type": "module"in package.json) - All imports use
.jsextensions for TypeScript files - No CommonJS
Security Features
- Input validation with regex patterns (alphanumeric +
-_.only) - Path sanitization to prevent
../traversal - Base path boundary checking
- File size limits (3MB for docs, 1MB for components)
- Safe error messages (no internal details exposed)
Caching
- LRU cache with 5-minute timeout
- Cache keys use full resolved file paths
- Improves performance for repeated documentation queries
License
MIT
Credits
- Design patterns abstracted from professional Next.js templates
- Catalyst components from Tailwind Labs
- Documentation from official Next.js and Tailwind CSS sources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.