Infrastruktur-Sichtbarkeit über Clouds hinweg für KI-Agenten. Diagnostizieren Sie Probleme über AWS, Vercel, GCP und Cloudflare hinweg, ohne jemals Ihren Editor zu verlassen.
Schmerzpunkt | CloudPulse-Lösung |
Frontend-Fehler auf Vercel → AWS-Konsole öffnen |
|
KI sieht nicht, ob eine SG Port 5432 blockiert |
|
Lambda-Nebenläufigkeitslimits werden erreicht |
|
Topologie vor dem Debugging unbekannt |
|
Related MCP server: Daemoon
npx cloudpulse-mcpDer Server erkennt automatisch die auf Ihrem Computer vorhandenen Anmeldedaten (AWS CLI, Umgebungsvariablen usw.).
Claude Desktop – hinzufügen zu ~/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 – hinzufügen zu .cursor/mcp.json in Ihrem Projekt:
{
"mcpServers": {
"cloudpulse": {
"command": "npx",
"args": ["-y", "cloudpulse-mcp"],
"env": {
"VERCEL_TOKEN": "<your-vercel-token>",
"AWS_REGION": "us-east-1"
}
}
}
}VS Code + GitHub Copilot (Agent Mode) – erfordert VS Code 1.99+ und die GitHub Copilot-Erweiterung.
Zuerst das Projekt bauen:
npm run buildDann .vscode/mcp.json in diesem Repository erstellen:
{
"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} liest aus Ihrer Shell-Umgebung – keine Geheimnisse in der Versionsverwaltung.
Zur Verwendung: Öffnen Sie den Copilot Chat, wechseln Sie in den Agent-Modus, klicken Sie auf Select Tools und aktivieren Sie die CloudPulse-Tools, dann fragen Sie ganz natürlich:
Why can't my Vercel project reach AWS RDS instance "my-db"?CloudPulse folgt einer Read-only, No-Storage-Richtlinie:
Anmeldedaten | Bereitstellung |
AWS |
|
Vercel |
|
Vercel Team |
|
GCP |
|
Cloudflare |
|
Es werden keine Anmeldedaten protokolliert oder gespeichert. Alle Werte werden zum Zeitpunkt des Aufrufs aus Umgebungsvariablen gelesen.
list_cloud_topologyScannen Sie alle konfigurierten Plattformen und geben Sie eine einheitliche Dienstkarte zurück.
Input (all optional):
platforms – ["aws", "vercel"] filter platforms
aws_region – "us-east-1"get_correlated_logsAbrufen und Zusammenführen von Protokollen von Vercel + AWS CloudWatch in einer Zeitachse.
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_linkÜberprüfen Sie, warum Dienst A die Ressource B nicht erreichen kann.
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_regionDurchgeführte Prüfungen:
Vercel-Umgebungsvariablen enthalten eine DATABASE_URL / DB_URL
AWS Security Group erlaubt eingehendes TCP auf dem erforderlichen Port
Externer API-HEAD-Erreichbarkeitstest
check_resource_limitsFragen Sie Kontingente ab und markieren Sie Ressourcen, die ihre Limits erreichen.
Input (all optional):
platforms – filter platforms
warn_threshold – usage % to warn at (default 80)
aws_regionPhase | Status | Umfang |
1 – MVP | ✅ Fertig | Vercel + AWS (Lambda, RDS, CloudWatch, Security Groups, S3) |
2 – Erweitern | ✅ Fertig | GCP Cloud Run + Cloud SQL + Logging; Cloudflare Workers + Pages; S3 CORS |
3 – Intelligenz | 🔜 | Vorgefertigte Diagnose-Playbooks für CORS, 504-Timeout, Cold-Start-Schleifen |
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.tsErstellen Sie src/providers/<platform>/index.ts und exportieren Sie:
is<Platform>Configured(): boolean
Provider-spezifische Datenfunktionen
Binden Sie die Funktionen in die entsprechenden Tools unter src/tools/ ein
Fügen Sie den Plattformnamen zur CloudPlatform-Union in src/types.ts hinzu
MIT © CloudPulse Contributors
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.
