Control Plane

io.cplnPublished by cpln.ioOfficial publisherv1.0.2Updated Oct 24, 2026

Control Plane (controlplane.com): deploy and operate workloads across AWS, GCP, Azure, and more.

VerifiedStreamable HTTPWeb executableCloud & InfrastructureDeveloper Tools

Overview

AI-generated overview

Hosted Control Plane MCP server that lets an assistant deploy, troubleshoot, secure and migrate containerized workloads across clouds.

What you can do
  • Deploy and operate containerized workloads across AWS, GCP, Azure, OCI and own hardware through one API
  • Troubleshoot workloads, including guided diagnosis of restarting or failing services
  • Configure networking, auto-TLS, autoscaling, access control, observability and stateful storage such as Postgres
  • Migrate Kubernetes, Compose or Helm configurations to Control Plane and apply them
  • Work with domain skills, guardrails and a short always-on rule set that the assistant applies in every session
When to use it
Useful when you already run or plan to run workloads on Control Plane and want an assistant to deploy, debug, secure or migrate them from natural-language requests, including Kubernetes migration and production changes that need confirmation.
Requirements
Remote hosted endpoint at mcp.cpln.io over streamable HTTP; OAuth 2.1 with PKCE sign-in through the MCP client, granting specific Control Plane organizations. Optional environment variables CPLN_TOKEN, CPLN_ORG, CPLN_GVC and CPLN_PROFILE support CLI workflows. Some skills run local tools such as cpln, docker, kubectl, helm, terraform, pulumi or cloud CLIs with your own credentials.
Before you install
MCP access is production access to the organizations you grant, limited by your own RBAC. Destructive actions such as deleting resources, shrinking volumes, replacing workloads or applying to production require explicit confirmation. CPLN_TOKEN is a sensitive service-account token. Skills may run local tools that send data to the Control Plane API, registries, your Kubernetes cluster or cloud accounts. Created resources persist in your org until deleted and are recorded in its audit trail.

Installation

In SourceWeft

  1. Open Control Plane in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.cpln%2Fcontrol-plane/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "control-plane": {
      "type": "http",
      "url": "https://mcp.cpln.io/mcp"
    }
  }
}

README

[Control Plane]

Control Plane AI Plugin

Run containerized workloads across AWS, GCP, Azure, OCI, and your own hardware under one API. It loads Control Plane's domain knowledge, production guardrails, and live MCP tools into Claude Code, Codex, and Antigravity CLI so your assistant can deploy, troubleshoot, secure, and migrate workloads with verified cpln commands.

Installation

Claude Code

text
/plugin marketplace add https://github.com/controlplane-com/ai-plugin.git/plugin install cpln@controlplane/reload-plugins

Update with /plugin marketplace update controlplane then /reload-plugins (third-party marketplaces don't auto-update unless you enable it in /plugin → Marketplaces).

Alternatively, install from Anthropic's community plugin marketplace, where every listing has passed Anthropic's review:

text
/plugin marketplace add anthropics/claude-plugins-community/plugin install cpln@claude-community/reload-plugins

Codex

bash
codex plugin marketplace add https://github.com/controlplane-com/ai-plugin.git

Start Codex, open /plugins, and install cpln. The MCP handshake supplies the core rules. Local installations also include optional session hooks, which must be reviewed and trusted in Codex before they run.

Update with codex plugin marketplace upgrade controlplane, then restart Codex.

Antigravity CLI

Install the plugin with Antigravity CLI (agy):

bash
agy plugin install https://github.com/controlplane-com/ai-plugin/plugins/cpln

Generic MCP client

Point any other MCP client at the hosted server:

json
{  "mcpServers": {    "cpln": {      "type": "http",      "url": "https://mcp.cpln.io/mcp"    }  }}

The bare URL serves the default core tool set. A client that loads tools on demand can add ?toolsets=full for every tool.

Authentication

MCP uses OAuth 2.1 + PKCE. Sign in to let the assistant act on your Control Plane organizations — you choose which orgs it may operate on, and the token is scoped to those orgs and enforced server-side on every call. Sign in again to change the grant. Treat MCP access as production access to the orgs you grant. How to sign in:

  • Claude Code — /mcp, select cpln, sign in (or claude mcp login cpln).
  • Codex — codex mcp login cpln.
  • Antigravity CLI — /mcp, select cpln, authenticate.

Environment variables

Optional — only for the cpln CLI workflows some skills generate (CI/CD, Terraform, Pulumi). See .env.example.

VariablePurpose
CPLN_TOKENService-account token for cpln CLI calls (sensitive).
CPLN_ORGDefault organization.
CPLN_GVCDefault GVC.
CPLN_PROFILELocal cpln CLI profile.

Usage

Ask in natural language — the assistant routes to the right skill or agent:

  • "Troubleshoot why my payments-api workload in production keeps restarting."
  • "Put app.example.com in front of my web workload with auto-TLS."
  • "Give my analytics workload credential-free read access to S3 bucket prod-event-logs — no IAM keys."
  • "Provision a production Postgres with HA failover and S3 backups."
  • "Convert this kustomization.yaml to Control Plane and apply it to staging after I confirm."

Two workflows also have slash commands in Claude Code — /cpln:troubleshoot WORKLOAD and /cpln:migrate-k8s FILE; in other clients, ask for the same workflows by name.

What's included

  • Domain skills across CLI usage, access control, autoscaling, networking, observability, migration, templates, stateful storage, and security.
  • Two guided agents: workload troubleshooting and Kubernetes / Compose / Helm migration.
  • A short always-on rule set the assistant applies in every session, with the full operating guide as a skill read on demand.
  • Pre-configured access to the hosted Control Plane MCP server.

Security

  • MCP access is production access — scoped to the orgs you grant and your own RBAC.
  • Destructive actions (deleting resources, shrinking/deleting volumes, replacing workloads, applying to production) require explicit confirmation.
  • Secret values never pass through the chat: Control Plane generates the values nobody needs to know, the user types their own values into the Console, and tools return secret metadata only.
  • The plugin stores no logs, secrets, prompts, or telemetry; your AI client and model provider process prompts per their own policies.

Report vulnerabilities per SECURITY.md.

Where data goes

The plugin's one declared connector is the hosted MCP server at https://mcp.cpln.io/mcp, which acts only on the orgs you grant when you sign in, with your own permissions.

When a task needs it, the skills also run these tools on your machine, each with your own credentials:

ToolSends data to
cpln CLIThe Control Plane API (api.cpln.io), your org's image registry (ORG.registry.cpln.io), and the metrics endpoint (metrics.cpln.io), using your CLI profile or CPLN_TOKEN
dockerThe image registries you push to and pull from
kubectl, helmThe Kubernetes cluster you point them at, when migrating from it or installing the Control Plane Kubernetes operator
terraform, pulumiThe Control Plane API, through the Control Plane provider
gcloud and other cloud CLIsYour own cloud account, when connecting a private network or creating an agent VM
curlYour own domain, to check it after setup

The plugin itself stores nothing. Resources, app files, and invitations the assistant creates are stored in your Control Plane org until you delete them, and the org's audit trail records each change.

More

Source: README.md at commit bc117b8

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts