Skip to main content
This page provides practical examples of how to interact with Control Plane through AI assistants using the MCP Server. These examples work across all compatible tools.

​
Setting Context

Before performing operations, always set your organization and GVC context: 
Use org "my-org" and gvc "my-gvc" for the following operations.
Setting context once at the start of a conversation helps the AI assistant understand which resources to target.

​
GVC Operations

​
Create a GVC

Create a new Global Virtual Cloud with specific locations. You can use friendly location names or technical location IDs: 
Create a new GVC called "production" with locations in Frankfurt, Virginia, and Dublin.
You can use friendly location names (like “Frankfurt”, “Virginia”, “Dublin”) or technical location IDs (like “aws-eu-central-1”, “aws-us-east-1”). The MCP server will resolve friendly names to the appropriate location IDs.

​
List GVCs

Show me all GVCs in the org "my-org".

​
Get GVC Details

Get the details of GVC "production" including its locations and configuration.

​
Workload Operations

​
Create a Workload

Create a new workload with various configurations: 
Create a publicly accessible workload called "api-server" with:
- Image: nginx:latest
- Port: 80
- Memory: 256Mi
- CPU: 250m

​
Update a Workload

Scale the workload "api-server" to a minimum of 3 replicas and maximum of 5 replicas.

​
List Workloads

List all workloads in GVC "production" with their current replica counts and status.

​
Get Workload Status

Show me the detailed status of workload "api-server" including:
- Current replicas
- Deployment status per location
- Recent events or errors

​
Delete a Workload

Delete the workload "old-service" from GVC "staging".
Deletion operations are irreversible. The AI assistant should be configured to confirm before executing destructive operations.

​
Image Operations

​
Build an Image

The cpln CLI must be installed and configured with a profile that is authenticated to the target organization. If no Dockerfile is present, the cpln image build command will use buildpacks to automatically create an image. Control Plane images are built for the linux/amd64 platform.
Build and push a container image to the Control Plane private registry: 
Build and push an image called "my-app:v1.0.0" from the current directory 
to the Control Plane registry in org "my-org".

​
List Images

Show me all images in org "my-org" with their tags and creation dates.

​
Get Image Details

Get the details of image "my-app" including all available tags and their digests.

​
Complex Workflows

​
Full Application Deployment

Deploy a complete application stack to Control Plane:

1. Create a GVC called "my-app-prod" in Frankfurt and Virginia

2. Create a publicly accessible workload "frontend" with:
   - Image: httpd:latest
   - Port: 80
   - Memory: 512Mi
   - CPU: 500m
   - 2-5 replicas

3. Create a publicly accessible workload "backend" with:
   - Image: nginx:latest
   - Port: 8080
   - Memory: 1Gi
   - CPU: 500m
   - 2-5 replicas
   - Environment variable SERVICE_NAME=backend

​
Environment Promotion

Promote the configuration from GVC "staging" to "production":
1. Get the current workload configurations from staging
2. Update the production workloads to match staging
3. Show me the differences before and after

​
Debugging Session

Help me debug the workload "api-server" in production:
1. Show me the current status and replica count
2. Check if there are any error events
3. Get the recent logs if possible
4. Show me the resource utilization

​
Best Practices

Start with Context

Always set your org and GVC context at the start of a conversation

Be Specific

Provide specific values for resources (memory, CPU, replicas) when possible

Confirm Destructive Actions

Configure your AI assistant to confirm before executing delete or update operations

Use Tags

Add tags to resources for better organization and filtering
For the best results, structure your prompts with:
  1. Context: Org and GVC
  2. Action: What you want to do
  3. Target: Which resource
  4. Details: Specific configuration values
Using org "my-org" and GVC "production", create a workload called "api-v2" 
with image nginx:latest, 512Mi memory, port 8080, and minimum 2 replicas.

​
Next Steps

Tool Setup

Configure MCP for your preferred tool

Workload Reference

Learn more about workload configuration options

GVC Concepts

Understand Global Virtual Clouds

Policy Reference

Configure permissions for your service account