Skip to main content
The Control Plane MCP Server lets any AI tool with Model Context Protocol support manage Control Plane resources through natural-language conversations.
If your AI tool supports plugins — Claude Code, Codex, or Gemini CLI — start with the Control Plane AI Plugin instead. The plugin auto-configures this MCP server and adds skills, agents, commands, and guardrails on top.

​
Endpoint

​
url
string
required
https://mcp.cpln.io/mcp

​
Authentication

OAuth with per-org consent. Your AI tool walks you through it on first use — see your tool’s setup page below for the exact trigger.

​
Toolset profiles

The full tool catalog is larger than most AI tools can hold in context at once — and some clients cap how many tools they accept. So each connection selects a toolset profile with the toolsets query parameter. The profiles are nested (each is a superset of the one above) — pick one:
ProfileWhat it includes
core (default)The everyday deploy-and-operate journey: GVCs, workloads, deployments, logs, secrets, images, custom domains, identities, policies, the template catalog, volume sets, Terraform export, and metrics — plus a generic read/delete tool that works on every resource kind, and a raw-API escape hatch for anything else.
mk8sEverything in core, plus the typed BYOK managed-Kubernetes (mk8s) cluster tools (create/update across all 11 providers).
fullEverything in mk8s, plus the full administrative and fine-tuning surface: cloud-account registration (AWS/GCP/Azure/NATS), org IAM (users, groups, service accounts, policy edits), every remaining secret type (AWS, GCP, Azure, NATS, TLS, key-pair, user/pass), network-bridge agents, identity network-resource bindings, IP sets, audit contexts, advanced workload tuning (load balancer, sidecar, rollout, security, retry, external logging), deep custom-domain editing (routes, ports, CORS, TLS), volume-set snapshots / expand / shrink, and org/GVC settings.
Examples
https://mcp.cpln.io/mcp                    # core (default)
https://mcp.cpln.io/mcp?toolsets=mk8s      # core + BYOK Kubernetes
https://mcp.cpln.io/mcp?toolsets=full      # everything
An unknown value returns a 400 listing the accepted names (core, mk8s, full).
Which profile should I use? Keep the default core for tools that load every tool definition up front — Cursor, Codex, Gemini CLI, ChatGPT, Claude Desktop, VS Code. Agents pick the right tool more reliably from a focused catalog, and core already covers the full build-and-operate workflow (it can read and delete any resource kind generically, and reach anything else through the raw-API tool). Use full only for clients with deferred tool loading — like Claude Code, which fetches tool definitions on demand and isn’t slowed by the larger catalog. Use mk8s when you manage BYOK Kubernetes clusters.
The profile is fixed for the life of a connection — an AI agent can’t expand it mid-session. If your assistant says a Control Plane tool isn’t available, reconnect with the profile that includes it.

​
Compatible tools

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

Claude Code

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

Claude Desktop

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

Claude Web

claude.ai in the browser
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/codex.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=7f6290d9a955377990c873b308593f35

Codex

OpenAI Codex
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/gemini.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=dd6f55dfadc4e39256e9ad1305b8c8e9

Gemini CLI

Google Gemini CLI
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/cursor.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=074f2c93b5c6063ae950a872e7821eb3

Cursor

Cursor IDE
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/vscode.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=68f269932eab223833a1c4f78d6be90a

VS Code

Visual Studio Code
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/antigravity.png?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=48d54825666f9af129853a040db724a6

Antigravity

Google Antigravity IDE
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/amp.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=727a834ec66ee41c3e405eb04f9097be

Amp

Sourcegraph Amp
https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/opencode.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=f58ee6d5c9eb2828f371a72d7ba8c8fc

OpenCode

OpenCode terminal assistant
Don’t see your tool listed? Any client that supports remote MCP servers can connect — point it at https://mcp.cpln.io/mcp and let it handle OAuth.

​
Next steps

https://mintcdn.com/controlplanecorporation/rFQpIcXts1y-5L7u/icons/mcp.svg?fit=max&auto=format&n=rFQpIcXts1y-5L7u&q=85&s=cb54e1afd80c8345d82dc3e4c9ca2e32

Tools Reference

Every tool the server exposes, grouped by resource, with toolset profiles

Usage Examples

Practical prompts for common Control Plane workflows

AI Plugin

Recommended path for Claude Code, Codex, Gemini CLI

Access Control

Scope what an AI tool can do in your org with policies and least privilege