> ## Documentation Index
> Fetch the complete documentation index at: https://docs.controlplane.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Amp

> Connect Amp, Sourcegraph's agentic coding tool, to Control Plane to operate your infrastructure from inside your editor or the Amp CLI.

## Prerequisites

<CardGroup cols={2}>
  <Card title="Amp" icon="https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/amp.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=727a834ec66ee41c3e405eb04f9097be" width="21" height="21" data-path="icons/amp.svg">
    Install [Amp](https://ampcode.com) for your editor or CLI
  </Card>

  <Card title="Control Plane account" icon="user">
    Sign up at [console.cpln.io](https://console.cpln.io) if you don't have an account yet
  </Card>
</CardGroup>

## Add the MCP server

<Steps>
  <Step title="Register the server">
    ```bash theme={null}
    amp mcp add cpln https://mcp.cpln.io/mcp
    ```

    <Note>
      Connecting to the bare URL uses the default **`core`** toolset profile — a focused set that already covers the whole build-and-operate workflow (it can read and delete any resource kind generically, and reach anything else through the raw-API tool), which is the right fit for this client. Append `?toolsets=mk8s` to add BYOK Kubernetes tools, or `?toolsets=full` for everything. See [toolset profiles](/ai/mcp#toolset-profiles).
    </Note>
  </Step>

  <Step title="Sign in">
    Launch the Amp CLI. Amp opens your browser automatically:

    1. Sign in to Control Plane (Google, GitHub, Microsoft, or SAML).
    2. Select the orgs you want Amp to access.
    3. Click **Authorize**.

    Your browser shows a success page — close the tab and return to Amp.
  </Step>

  <Step title="Use it">
    In Amp, ask "list GVCs in org `<your-org>`" (using one of the orgs you authorized) to confirm.
  </Step>
</Steps>

## Example conversation

<Steps>
  <Step title="Set Context">
    ```
    Use org "my-org" and gvc "my-gvc" for context.
    ```
  </Step>

  <Step title="Deploy a Workload">
    ```
    Create a publicly accessible workload called "my-api" using nginx:latest on port 80.
    ```
  </Step>

  <Step title="Get the Endpoint">
    ```
    Monitor the readiness of my-api and give me the public endpoint once it's ready.
    ```
  </Step>
</Steps>

## Next steps

<CardGroup cols={2}>
  <Card title="Usage Examples" icon="lightbulb" href="/ai/examples">
    Practical prompts for common Control Plane workflows
  </Card>

  <Card title="Template Catalog" icon="grid" href="/template-catalog/overview">
    30+ production-ready templates your AI can deploy on request
  </Card>
</CardGroup>