mcp-apps-generative-ui-showcase
Enables booking flights and hotels, creating investment portfolios, and managing kanban boards directly within a chat interface using generative UI components.
README
mcp-apps-generative-ui-showcase (Docker)
Empacotamento em container do MCP Apps Generative UI Showcase — reserve voos, hotéis, monte portfólios e gerencie um kanban dentro do chat. Cada ferramenta do servidor MCP é ligada a um app HTML/JS que a interface monta como um iframe sandbox na conversa (MCP Apps Extension, SEP-1865). Front Next.js com CopilotKit + AG-UI e um servidor MCP Node/Express que registra as ferramentas e serve os apps.
- Upstream (Apache-2.0): Shubhamsaboo/awesome-llm-apps —
generative_ui_agents/mcp-apps-generative-ui-showcase - Imagem:
ghcr.io/marcelofmatos/mcp-apps-generative-ui-showcase - Stack Portainer:
marcelofmatos/portainer-stacks→mcp-apps-showcase/
Arquitetura da imagem
Imagem combinada node-only (um único container roda os dois processos Node):
| Processo | Porta | Papel |
|---|---|---|
Next.js (next start) |
3000 |
UI web (exposta) — CopilotKit runtime; detém a OPENAI_API_KEY; fala com o MCP via MCP_SERVER_URL |
MCP server (node dist/server.js) |
3001 |
Interno — registra ferramentas e serve os apps HTML em /mcp; GET /health |
O entrypoint.sh sobe o servidor MCP em background e serve o front em foreground; se qualquer
um dos dois cair, o container encerra (o orquestrador reinicia).
Variáveis de ambiente
| Variável | Obrigatória | Default | Descrição |
|---|---|---|---|
OPENAI_API_KEY |
✅ | — | Chave OpenAI usada pelo CopilotKit runtime (front) |
MCP_SERVER_URL |
❌ | http://localhost:3001/mcp |
URL front→servidor MCP |
Uso rápido (Docker)
docker run --rm -p 3000:3000 \
-e OPENAI_API_KEY=sk-... \
ghcr.io/marcelofmatos/mcp-apps-generative-ui-showcase:latest
# abra http://localhost:3000
Experimente um dos prompts: "Book a flight from JFK to LAX on January 20th for 2 passengers", "Create a $10,000 tech-focused portfolio", "Create a kanban board for my software project".
Build e release
Imagem publicada pelo workflow 🚀 Release and build (workflow_dispatch): calcula a
próxima versão SemVer, cria tag + release e publica em ghcr.io/marcelofmatos/mcp-apps-generative-ui-showcase
com as tags x.y.z, x.y, x e latest. Build local:
docker build -t ghcr.io/marcelofmatos/mcp-apps-generative-ui-showcase:dev .
Licença
Código da aplicação sob Apache-2.0 (do upstream awesome-llm-apps). Ver LICENSE.
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.
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.
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.
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.