High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Flowbite MCP server for Figma and UI components
This MCP server connects your agent to Flowbite’s component library, theme generator, and Figma-to-code flow. You can use it in Claude, Cursor, Windsurf, or any MCP client that can talk to a local or HTTP server.

Builders who want their agent to pull Flowbite UI pieces, generate themes, or convert Figma nodes into code.
You can move from design to usable Flowbite UI code without leaving your agent workflow.
What it does
Figma to code
Turns a Figma node URL into code when you provide a Figma personal access token.
Theme file generator
Creates a custom branded theme from a hex color.
Flowbite component access
Exposes 60+ Flowbite UI components, including forms, typography, and plugins, as MCP resources.
Dual transport support
Runs in stdio for local clients or HTTP Streamable mode for server deployments.
Docker support
Includes a production-ready Docker setup with health checks and compose support.
How to get it
- 1The simplest way to use Flowbite MCP Server
npx flowbite-mcp
- 2Currently you only need the Figma personal access token if you want to enable the Figma…
// other options "env": { "FIGMA_ACCESS_TOKEN": "YOUR_PERSONAL_FIGMA_ACCESS_TOKEN" }
README
Official MCP server for Flowbite to leverage AI for UI creation and theme generation
An MCP server that enables AI assistants to access the Flowbite library of Tailwind CSS components—including UI elements, forms, typography, and plugins—while offering an intelligent theme generator for creating custom branded designs within AI-driven development environments.
MCP Features
Tools:
- 🎨 [NEW] Figma to code - Copy the Figma node url and generate code (video demo)
- 🎯 Theme file generator - Create custom branded themes from any branded hex color
Resources:
- 📦 60+ UI components - Complete access to the Flowbite UI components
Server:
- 🌐 Dual transport support - Standard I/O (stdio) for CLI or HTTP Streamable for server deployments
- ⚡ Production ready - Docker support with health checks and monitoring
Quickstart
Using NPX
The simplest way to use Flowbite MCP Server:
npx flowbite-mcp
Environment variables
Currently you only need the Figma personal access token if you want to enable the Figma to code generation tool.
// other options
"env": {
"FIGMA_ACCESS_TOKEN": "YOUR_PERSONAL_FIGMA_ACCESS_TOKEN"
}
You set this variable in your MCP client configuration file.
Integration examples
Use the following configuration examples to install the Flowbite MCP server in popular clients such as Cursor, Claude, Windsurf, and others.
Claude desktop
Update the claude_desktop_config.json file and add the following configuration:
{
"mcpServers": {
"flowbite": {
"command": "npx",
"args": ["-y", "flowbite-mcp"],
"env": {
"FIGMA_ACCESS_TOKEN": "YOUR_PERSONAL_FIGMA_ACCESS_TOKEN"
}
}
}
}
Cursor editor
Update the mcp.json file and add the following configuration:
{
"mcpServers": {
"flowbite": {
"command": "npx",
"args": ["-y", "flowbite-mcp"],
"env": {
"FIGMA_ACCESS_TOKEN": "YOUR_PERSONAL_FIGMA_ACCESS_TOKEN"
}
}
}
}
Windsurf editor
Update the mcp_config.json file and add the following configuration:
{
"mcpServers": {
"flowbite": {
"command": "npx",
"args": ["-y", "flowbite-mcp"],
"env": {
"FIGMA_ACCESS_TOKEN": "YOUR_PERSONAL_FIGMA_ACCESS_TOKEN"
}
}
}
}
Glama.ai
Local Transport Modes
Standard I/O (stdio)
The default mode for local development and CLI integrations:
# Start in stdio mode (default)
node build/index.js
{
"mcpServers": {
"flowbite": {
"command": "node",
"args": ["/path/to/flowbite-mcp/build/index.js"],
"env": {
"FIGMA_ACCESS_TOKEN": "YOUR_PERSONAL_FIGMA_ACCESS_TOKEN"
}
}
}
}
Learn how to get the Figma personal access token to enable the Figma to code generation tool.
HTTP server
HTTP-based transport for production and multi-client scenarios:
node build/index.js --mode http --port 3000
This will make the MCP server available at 'http://localhost:3000/mcp'.
Local development
# Clone the repository
git clone https://github.com/themesberg/flowbite-mcp.git
cd flowbite-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Run in stdio mode (for Claude Desktop, Cursor)
npm start
# Run inspector
npm run start inspector
# Run in HTTP server mode (for production/multi-client)
MCP_TRANSPORT_MODE=http npm start
Production deployment (HTTP Mode)
For production servers with multiple clients:
# Using npx
npx flowbite-mcp --mode http --port 3000
# Using Docker Compose
docker-compose up -d
# Health check
curl http://localhost:3000/health
Hosting variables
Configure the server behavior with these environment variables:
# Transport mode: stdio (default) or http
MCP_TRANSPORT_MODE=http
# Server port for HTTP mode
MCP_PORT=3000
# Host binding for HTTP mode
MCP_HOST=0.0.0.0
# CORS origins (comma-separated)
MCP_CORS_ORIGINS=http://localhost:3000,https://myapp.com
Docker Configuration
The project includes a production-ready Docker setup with multi-stage builds for optimal performance.
Quickstart with Docker
# Build and run with Docker Compose (recommended)
docker-compose up -d
# Check health
curl http://localhost:3000/health
# View logs
docker-compose logs -f
# Stop
docker-compose down
MCP inspector
Use the MCP Inspector for interactive debugging:
npm run inspector
Logging
Check server logs for detailed information:
# stdio mode logs to console
node build/index.js
# HTTP mode includes HTTP request logs
MCP_TRANSPORT_MODE=http node build/index.js
File structure
flowbite-mcp/
├── src/
│ ├── index.ts # Main server entry point
│ └── server-runner.ts # Express HTTP Streamable transport
├── data/
│ ├── components/ # 60+ component markdown files
│ ├── forms/ # Form component documentation
│ ├── typography/ # Typography elements
│ ├── plugins/ # Plugin documentation
│ ├── theme.md # Theme variable reference
│ └── quickstart.md # Getting started guide
├── build/ # Compiled JavaScript output
├── package.json
├── tsconfig.json
└── README.md
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
License
This project is licensed under the MIT License License - see the LICENSE file for details.
Credits
- Flowbite - For the amazing Tailwind CSS component library
- Anthropic - For the Model Context Protocol specification
- Tailwind CSS - For the utility-first CSS framework
Resources
- 🎨 Flowbite Documentation
- 📦 Flowbite Components
- 🌐 Model Context Protocol
- 🚀 Tailwind CSS v4 Docs
- 💬 GitHub Issues
Roadmap
- Complete component resource access
- AI-powered theme generator
- Dual transport support (stdio + HTTP)
- Flowbite Pro blocks integration (with license authentication)
- Figma to code conversion tool
- Enhanced theme customization options
- Component search and filtering
- Real-time component preview generation
Files in the repo
- .claude-plugin
- data
- src
- .dockerignore
- .gitignore
- .npmignore
- DOCKER_GUIDE.md
- docker-compose.yml
- Dockerfile
- glama.json
- LICENSE.md
- mcp-config.json
- NPM_PUBLISHING.md
- package-lock.json
- package.json
- README.md
- server.json
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。