Skip to main content

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.

Connectors sync across Claude. Setting this up on claude.ai also enables it in the Claude desktop app, and vice versa — you only need to do it once.

Prerequisites

https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/claude.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=8b0f9fcceff42ac846ff975af5126fb4

Claude.ai account

Sign in at claude.ai

Control Plane account

Sign up at console.cpln.io if you don’t have an account yet

Add the MCP server

1

Open Connector settings

2

Add a Custom Connector

Click the + button, then Add custom connector, and fill in:
FieldValue
NameControl Plane
Remote MCP server URLhttps://mcp.cpln.io/mcp
Click Add.
3

Connect

On the new Control Plane connector card, click Connect. Claude opens a new tab for sign-in.
  1. Sign in to Control Plane (Google, GitHub, Microsoft, or SAML).
  2. Select the orgs you want claude.ai to access.
  3. Click Authorize.
The tab closes automatically and the connector shows as Connected.
4

Use it

Open a new chat. The Control Plane tools are now available — try asking Claude to “list GVCs in org <your-org>” (using one of the orgs you authorized) to confirm.
For the latest connector setup details, see Anthropic’s Custom Connectors documentation.

Example conversation

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

Go to claude.ai/customize/connectors, disconnect the Control Plane connector, then click Connect again. Sign in and adjust your org selections on the consent screen.

Next steps

Usage Examples

Practical prompts for common Control Plane workflows

Template Catalog

30+ production-ready templates your AI can deploy on request