Skip to main content
Connect Visual Studio Code to Control Plane using GitHub Copilot’s MCP support to manage your infrastructure from your editor.
For detailed information on MCP servers in VS Code, refer to the official VS Code MCP documentation.

​
Prerequisites

VS Code & GitHub Copilot Extension

Download VS Code and install the GitHub Copilot extension

Service Account Token

Create a service account with appropriate permissions

​
Configuration

1

Open MCP Configuration

Open the Command Palette (Cmd/Ctrl + Shift + P) and run MCP: Open User Configuration. This will open the mcp.json configuration file.
2

Add the MCP Server

Add the Control Plane MCP Server configuration:
{
  "servers": {
    "cpln": {
      "url": "https://mcp.cpln.io/mcp",
      "type": "http",
      "headers": {
        "Authorization": "<your-service-account-token>"
      }
    }
  },
  "inputs": []
}
Replace <your-service-account-token> with your actual service account token.
3

Save and Reload

Save the configuration file. VS Code will automatically reload the MCP server configuration.

​
Verify the Connection

Open GitHub Copilot Chat and ask: 
List all cpln mcp server tools
GitHub Copilot should list the available Control Plane MCP tools.

​
Example Usage

1

Set Context

Use org "my-org" and gvc "my-gvc" for context.
2

Deploy a Workload

Create a publicly accessible workload called "my-api" using nginx:latest on port 80.
3

Get the Endpoint

Monitor the readiness of my-api and give me the public endpoint once it's ready.

​
Troubleshooting

  • Check that your service account token is valid.
  • Ensure the token is entered without extra spaces or quotes.
  • Verify the token has appropriate permissions (see Service Account Permissions).
  • Check for typos in the org name you’re using for context, this is a common cause of authentication failures.

​
Next Steps

Usage Examples

See practical examples of Control Plane operations

Policy Reference

Learn about permissions and access control