Laboratorio MCP Gateway
Connects multiple microservices (ventas and pedidos) through a central MCP gateway, enabling Claude Desktop to invoke sales and order tools via STDIO.
README
Laboratorio MCP — Integración con Claude Desktop
Descripción
Este laboratorio implementa una integración completa del Model Context Protocol (MCP), conectando múltiples microservicios (ventas y pedidos) a través de un gateway central.
El sistema permite que Claude Desktop invoque herramientas MCP locales mediante comunicación STDIO.
Estructura del proyecto
packages/
├─ mcp-ventas-node/ → Servidor Node.js que maneja operaciones de ventas
├─ mcp-pedidos-py/ → Servidor Python que gestiona pedidos
└─ mcp-gateway/ → Gateway que expone ambos servicios como un único MCP
Pasos de ejecución
Iniciar la base de datos
Ejecuta el contenedor PostgreSQL:
docker compose up -d
Esto levanta una instancia con las credenciales
Host: localhost
Puerto: 5433
Usuario: postgres
Contraseña: postgres
Base de datos: mcp_lab
Ejecutar los servidores de negocio
Servidor de pedidos (Python)
cd packages/mcp-pedidos-py
source .venv/bin/activate
python3 server.py
Servidor ventas (Node.js)
cd packages/mcp-ventas-node
npm run build
node dist/server.js
Gateway MCP
Este gateway conecta ambos microservicios el ecosistema MCP
cd packages/mcp-gateway
chmod +x run-gateway.sh
./run-gateway.sh
Debería salir un mensaje como este
[ventas] DB mode=postgres
[pedidos] INFO DB mode=postgres
Integración con Claude Desktoop
Crea o edita el archivo
nano ~/Library/Application\ Support/Claude/claude_desktop_config.json
Debería salir un mensaje como este
{
"mcpServers": {
"mcp-gateway": {
"command": "/TuDireccion/Laboratorio MCP/packages/mcp-gateway/run-gateway.sh",
"args": []
}
}
}
Nota: para la implementación en MAC se le debe dar permisos a Claude Desktop para acceder al disco
Claude Desktop



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.
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.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.