Store MCP Demo
A demo MCP server built with Node.js and TypeScript that showcases tools, resources, and prompts via stdio, including product search, stock checks, and order placement for a mock store.
README
Store MCP Demo
Este projeto cria um servidor MCP simples em Node.js + TypeScript para demonstrar, ao vivo, os conceitos de tools, resources e prompts com transporte stdio.
Requisitos
- Node.js 20+
- npm
Como rodar
npm install
npm run build
npm start
O servidor fica aguardando mensagens MCP via stdio.
Conectar no MCP Inspector
Para testar visualmente antes da apresentação:
npx @modelcontextprotocol/inspector
No inspector, escolha a opção de conexão via stdio e rode o comando:
npm start
Conectar no GitHub Copilot Chat no VS Code
Crie um arquivo .vscode/mcp.json na raiz do projeto com o seguinte conteúdo:
{
"servers": {
"store-mcp-demo": {
"type": "stdio",
"command": "node",
"args": ["c:/Business/Programmers/AI/Presentation/github_copilot_mcp/dist/server.js"]
}
}
}
Lembretes importantes:
- O MCP só fica visível no modo Agent do Copilot Chat, não em Ask/Edit.
- O VS Code pede confirmação antes de cada execução de tool.
Estrutura do projeto
- src/server.ts: setup do servidor MCP e registro das primitivas
- src/tools: implementação das tools
- src/resources: implementação dos resources
- src/prompts: implementação dos prompts
- src/data: dados mockados em JSON
Demonstração rápida
A demo pode seguir esta ordem:
- Listar tools
- Consultar o catálogo via resource
- Buscar produtos com search_products
- Ler detalhes de um produto com get_product_details
- Consultar estoque com check_stock
- Criar um pedido com place_order para mostrar efeito colateral
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.