Visibilidad de infraestructura entre nubes para agentes de IA. Diagnostica problemas en AWS, Vercel, GCP y Cloudflare sin salir nunca de tu editor.
Punto de dolor | Solución de CloudPulse |
Error de frontend en Vercel → debo abrir la consola de AWS |
|
La IA no puede ver si un SG bloquea el puerto 5432 |
|
Alcanzar límites de concurrencia de Lambda silenciosamente |
|
Topología desconocida antes de depurar |
|
Related MCP server: Daemoon
npx cloudpulse-mcpEl servidor detecta automáticamente las credenciales ya presentes en tu máquina (AWS CLI, variables de entorno, etc.).
Claude Desktop – añade a ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"cloudpulse": {
"command": "npx",
"args": ["-y", "cloudpulse-mcp"],
"env": {
"VERCEL_TOKEN": "<your-vercel-token>",
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}Cursor – añade a .cursor/mcp.json en tu proyecto:
{
"mcpServers": {
"cloudpulse": {
"command": "npx",
"args": ["-y", "cloudpulse-mcp"],
"env": {
"VERCEL_TOKEN": "<your-vercel-token>",
"AWS_REGION": "us-east-1"
}
}
}
}VS Code + GitHub Copilot (Modo Agente) – requiere VS Code 1.99+ y la extensión GitHub Copilot.
Primero, compila el proyecto:
npm run buildLuego crea .vscode/mcp.json en este repositorio:
{
"servers": {
"cloudpulse": {
"type": "stdio",
"command": "node",
"args": ["${workspaceFolder}/dist/index.js"],
"env": {
"VERCEL_TOKEN": "${env:VERCEL_TOKEN}",
"AWS_REGION": "${env:AWS_REGION}",
"AWS_PROFILE": "${env:AWS_PROFILE}"
}
}
}
}${env:VAR} lee desde el entorno de tu shell — sin secretos en el control de versiones.
Para usar: abre Copilot Chat, cambia al modo Agente, haz clic en Select Tools y habilita las herramientas de CloudPulse, luego pregunta de forma natural:
Why can't my Vercel project reach AWS RDS instance "my-db"?CloudPulse sigue una política de solo lectura, sin almacenamiento:
Credencial | Cómo proporcionar |
AWS |
|
Vercel |
|
Vercel Team |
|
GCP |
|
Cloudflare |
|
No se registran ni almacenan credenciales. Todos los valores se leen de las variables de entorno en el momento de la llamada.
list_cloud_topologyEscanea todas las plataformas configuradas y devuelve un mapa de servicios unificado.
Input (all optional):
platforms – ["aws", "vercel"] filter platforms
aws_region – "us-east-1"get_correlated_logsObtiene y fusiona registros de Vercel + AWS CloudWatch en una sola línea de tiempo.
Input:
start_time * – ISO-8601 or epoch ms e.g. "2024-06-01T10:00:00Z"
end_time – defaults to now
trace_id – filter by trace/request ID across all sources
aws_log_group_prefix – default "/aws/lambda"
vercel_project – project name or ID
aws_regiondiagnose_service_linkComprueba por qué el servicio A no puede llegar al recurso B.
Input:
source_service * – "vercel" | "lambda" | "ec2" | ...
target_resource * – "<type>:<id>" e.g. "aws-rds:my-db", "external-api:https://..."
port – auto-detected (5432 for RDS, 443 for APIs, ...)
vercel_project
aws_regionComprobaciones realizadas:
Las variables de entorno de Vercel contienen una DATABASE_URL / DB_URL
El grupo de seguridad de AWS permite TCP entrante en el puerto requerido
Prueba de alcanzabilidad HEAD de API externa
check_resource_limitsConsulta cuotas y marca los recursos que se acercan a sus límites.
Input (all optional):
platforms – filter platforms
warn_threshold – usage % to warn at (default 80)
aws_regionFase | Estado | Alcance |
1 – MVP | ✅ Hecho | Vercel + AWS (Lambda, RDS, CloudWatch, Security Groups, S3) |
2 – Extensión | ✅ Hecho | GCP Cloud Run + Cloud SQL + Logging; Cloudflare Workers + Pages; S3 CORS |
3 – Inteligencia | 🔜 | Libros de jugadas de diagnóstico preconstruidos para CORS, tiempo de espera 504, bucles de arranque en frío |
git clone https://github.com/Galadriel-Tech-Solutions/cloudpulse-mcp
cd cloudpulse-mcp
npm install
npm run dev # run from source with tsx
npm run build # compile to dist/src/
├── index.ts # MCP server + tool registration
├── types.ts # shared domain types
├── utils.ts # concurrency, formatting helpers
├── providers/
│ ├── aws/
│ │ ├── index.ts # client factory + isAWSConfigured()
│ │ ├── cloudwatch.ts # CloudWatch Logs
│ │ ├── lambda.ts # Lambda function listing
│ │ ├── rds.ts # RDS/Aurora instances & clusters
│ │ ├── ec2.ts # Security Group inspection
│ │ ├── s3.ts # S3 buckets + CORS checks
│ │ └── quotas.ts # Service Quotas API
│ ├── gcp/
│ │ ├── index.ts # isGCPConfigured() + resolveGCPProject()
│ │ ├── cloud-run.ts # Cloud Run services
│ │ ├── cloud-sql.ts # Cloud SQL instances (sqladmin v1beta4)
│ │ └── logging.ts # Cloud Logging
│ ├── cloudflare/
│ │ └── index.ts # Pages, Workers, Worker tail logs (WebSocket)
│ └── vercel/
│ └── index.ts # Vercel REST API v9
└── tools/
├── list-cloud-topology.ts
├── get-correlated-logs.ts
├── diagnose-service-link.ts
└── check-resource-limits.tsCrea src/providers/<plataforma>/index.ts exportando:
is<Plataforma>Configured(): boolean
Funciones de datos específicas del proveedor
Conecta las funciones en las herramientas relevantes bajo src/tools/
Añade el nombre de la plataforma a la unión CloudPlatform en src/types.ts
MIT © Colaboradores de CloudPulse
Query quota limits and current usage across configured cloud platforms. Highlights resources approaching or exceeding their limits (default warning threshold: 80%). Use this to proactively catch Lambda concurrency limits, Vercel plan caps, and similar issues before they cause outages.
Inputs: platforms, warn_threshold, aws_region.
Diagnose connectivity issues between a source service and a target resource. Checks Vercel environment variables, AWS Security Group inbound rules on the required port, and external API reachability. Returns a list of diagnostic results with actionable messages.
Inputs: source_service (required), target_resource (required), port, aws_region, +2 more.
Scan all configured cloud platforms (AWS, Vercel, GCP, Cloudflare) and return a unified topology of active services including their endpoints and regions. Run this first to understand the infrastructure landscape.
Inputs: platforms, aws_region.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: check_resource_limits focuses on quota monitoring, diagnose_service_link on connectivity diagnostics, get_correlated_logs on log aggregation, and list_cloud_topology on infrastructure discovery. The descriptions reinforce unique scopes, making misselection unlikely.
All tool names follow a consistent verb_noun pattern (e.g., check_resource_limits, diagnose_service_link), using snake_case uniformly. This predictability aids agent understanding and tool selection without confusion.
Four tools is a reasonable count for a cloud monitoring server, covering key areas like limits, diagnostics, logs, and topology. It feels slightly lean but well-scoped, as each tool addresses a distinct monitoring need without bloat.
The toolset covers core cloud monitoring workflows: proactive limits checking, connectivity diagnosis, log correlation, and topology mapping. Minor gaps exist, such as lack of alerting or remediation tools, but agents can work around these with the provided diagnostic and data-fetching capabilities.
Errors, logs and AI-call costs for apps on Node.js, Next.js, Cloudflare Workers or the browser. Ask your AI what’s broken, why, and how to fix it, right inside Cursor or Claude.
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
AI agent observability for production traces, natural-language insights, and improvement loops.
Data + AI observability — monitor and troubleshoot production-grade agents and the context they use.
