Designed for deployment on Google Cloud Run with containerization support, automatic scaling, and integrated monitoring for CPU/memory usage, requests, latency, and errors.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Filesystem Server list the files in the /tmp directory"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Servidor MCP (Model Context Protocol) adaptado para producción en Google Cloud Platform.
🔒 Seguridad: Control de acceso a directorios específicos
🔑 Autenticación: API Key opcional
📁 Operaciones de archivos: Leer, escribir, editar, buscar
🌐 HTTP/SSE Transport: Compatible con Cloud Run
🐳 Containerizado: Listo para desplegar
Related MCP server: MCP Filesystem Server
Google Cloud SDK (gcloud)
Proyecto de GCP configurado
APIs habilitadas: Cloud Run, Cloud Build, Container Registry
# 1. Configurar tu proyecto GCP
gcloud config set project YOUR_PROJECT_ID
# 2. Ejecutar script de despliegue
./deploy.shEl script:
Habilita las APIs necesarias
Construye la imagen Docker
Despliega a Cloud Run
Genera una API Key automáticamente
Muestra la URL del servicio
PORT: Puerto del servidor (default: 8080)
ALLOWED_DIRS: Directorios permitidos, separados por comas
API_KEY: Clave de autenticación (opcional)
# Build
gcloud builds submit --tag gcr.io/PROJECT_ID/mcp-filesystem-server
# Deploy
gcloud run deploy mcp-filesystem-server \
--image gcr.io/PROJECT_ID/mcp-filesystem-server \
--region us-central1 \
--set-env-vars "ALLOWED_DIRS=/tmp,API_KEY=tu-clave-segura"curl https://your-service-url.run.app/healthConfigure su cliente MCP para conectarse a:
URL: https://your-service-url.run.app/sse
Header: X-API-Key: your-api-key
read_file: Leer archivos
write_file: Escribir archivos
edit_file: Editar archivos con diffs
create_directory: Crear directorios
list_directory: Listar contenido
directory_tree: Árbol de directorios
move_file: Mover/renombrar archivos
search_files: Buscar archivos
get_file_info: Información de archivos
list_allowed_directories: Ver directorios permitidos
Solo accede a directorios explícitamente permitidos
Validación de rutas para prevenir acceso no autorizado
Autenticación por API Key
Usuario no-root en el container
Manejo seguro de señales con dumb-init
Cloud Run proporciona métricas automáticas:
Requests por segundo
Latencia
Errores
Uso de CPU/memoria
Cloud Run: ~$0.00002400/vCPU-segundo
Almacenamiento: Según Container Registry
Red: $0.12/GB egreso
Con auto-scaling, solo pagas por uso real.
gcloud services enable cloudbuild.googleapis.com cloudrun.googleapis.comAsegúrate de tener roles:
Cloud Run Admin
Cloud Build Editor
Storage Admin
gcloud run services logs read mcp-filesystem-server --region us-central1Incluye una interfaz web para gestionar archivos:
cd frontend
./deploy.sh📁 Explorador de archivos visual
✏️ Editor de texto integrado
🔐 Autenticación con API Key
💾 Crear, editar, eliminar archivos
📂 Gestión de directorios
Para usar con Claude Desktop, sigue las instrucciones en CLAUDE_DESKTOP_SETUP.md.
El proxy incluido (mcp-client-proxy.js) permite conectar Claude Desktop con el servidor remoto.
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Claude Desktop │────▶│ Proxy Local │────▶│ MCP Server │
│ (StdIO) │ │ (HTTP/SSE) │ │ (Cloud Run) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│
┌─────────────────┐ │
│ Frontend Web │───────────────────────────────────────┘
│ (Browser) │
└─────────────────┘MIT - Basado en el proyecto oficial de Anthropic
This server cannot be deployed
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
The BigQuery remote MCP server is a fully managed service that uses the Model Context Protocol to connect AI applications and LLMs to BigQuery data sources. It provides secure, standardized tools for AI agents to list datasets and tables, retrieve schemas, generate and execute SQL queries through natural language, and analyze data—enabling direct access to enterprise analytics data without requiring manual SQL coding.
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
