ZopNight ships an MCP server with 43 read-only tools for Claude Desktop, Cursor, Codex, and Claude Code. PAT authentication, RBAC at the gateway, audit-logged. AI assistants query resources, costs, recommendations, teams, and budgets in natural language. ZopNight applies ai cloud management to non-production across AWS, GCP, and Azure, measured against real usage. See it by cloud or by service below, and the discipline in FinOps.
By cloud
By service
- AI Cloud Management for EC2
- AI Cloud Management for RDS
- AI Cloud Management for EKS
- AI Cloud Management for ECS
- AI Cloud Management for Lambda
- AI Cloud Management for ElastiCache
- AI Cloud Management for Redshift
- AI Cloud Management for SageMaker
- AI Cloud Management for EMR
- AI Cloud Management for ASG
- AI Cloud Management for S3
- AI Cloud Management for EBS
- AI Cloud Management for CloudFront
- AI Cloud Management for DynamoDB
- AI Cloud Management for App Runner
- AI Cloud Management for Compute Engine
- AI Cloud Management for Cloud SQL
- AI Cloud Management for GKE
- AI Cloud Management for Cloud Run
- AI Cloud Management for Memorystore
- AI Cloud Management for BigQuery
- AI Cloud Management for Cloud Functions
- AI Cloud Management for Artifact Registry
- AI Cloud Management for Azure VMs
- AI Cloud Management for AKS
- AI Cloud Management for Azure SQL
- AI Cloud Management for Azure Functions
- AI Cloud Management for VMSS
- AI Cloud Management for Databricks
- AI Cloud Management for ML Compute
Questions we get a lot.
If yours isn't here, email us and we'll answer directly.
Where should I start?
Start with the FinOps overview for the discipline that ties it together, then use the specific guide, cloud, or location page for the task you are on.
Is production at risk?
No. Production is excluded by default; ZopNight acts only on the non-production resources you choose.
What access does ZopNight need?
A read-only role to start. Discovery, cost reporting, and recommendations all run read-only, and you enable actions when you are ready.
Which clouds are supported?
AWS, GCP, and Azure from one platform, including Databricks across all three. Schedules, groups, overrides, and recommendations work the same way regardless of provider.