Teach your AI coding agent to use Control Plane - Control Plane

Control Plane

2 min read Original article ↗

AI Plugin (Recommended)

For Claude Code, Codex, and Antigravity CLI. Includes the MCP server plus skills, agents, slash commands, and guardrails.

MCP Server

For any other MCP-compatible AI — Cursor, Claude Web, Claude Desktop, VS Code, Antigravity IDE, Amp, OpenCode.

What you can do

Manage Resources

Create and configure GVCs, workloads, identities, and more

Deploy Applications

Build images and deploy applications across global locations

Query Infrastructure

Get real-time information about your Control Plane resources

Automate Workflows

Streamline DevOps tasks through conversational AI

Which path for which tool?

Claude Code

Codex

Antigravity CLI

Antigravity IDE

MCP Server

Other MCP clients

Any remote-MCP client

Sign in

Each tool triggers OAuth its own way — see your tool’s setup page for the specifics. Once your browser lands on Control Plane:

Sign in to Control Plane

Use Google, GitHub, Microsoft, or SAML.

Authorize orgs

Pick the orgs this AI client may access and click Authorize.

Best practices

Authorize only the orgs you need

Per-client consent lets you scope each AI tool to the smallest org set that makes sense for its job

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

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.

References

AI Plugin

Install guide and the full inventory of skills, agents, commands, and guardrails

MCP Server

Endpoint and the compatible-tools list

Tools Reference

Every tool the MCP server exposes, grouped by resource

Usage Examples

Practical prompts for common Control Plane workflows

AI Plugin on GitHub

Source, release notes, and contribution guide