American Cloud MCP server: manage your cloud from Claude or Cursor

American Cloud has an official MCP server. It connects Claude, ChatGPT, Grok, Cursor, Codex, Windsurf, VS Code or any other MCP client to your account, so you can manage VMs, DNS, block and object storage, networking, managed Kubernetes, databases and WordPress in plain English.

It speaks the Model Context Protocol, the open standard these assistants use to call outside tools. Ask a question, get an answer. Give an instruction, watch it happen.

You: What's running in my account right now, and what does each VM cost per month?

You: Audit my firewall rules — is anything open to the whole internet that shouldn't be?

You: Spin up an Ubuntu VM in us-west with my SSH key and open ports 22, 80, and 443.

No scripts. No console tabs. No API documentation open in another window. One sign-in, or one config snippet, and your AI assistant becomes a capable cloud operator.

Two ways to connect

The hosted server needs no install. Add the address to your client and sign in to American Cloud in your browser. The app then acts as you, within your own role, and you control it from the Connected apps page.

The local server runs on your machine, over stdio. Your API token goes straight from your environment to the American Cloud API, with no hop in between. That's the same principle the rest of our platform is built on: your infrastructure, your keys, your control. If you care about why that matters, read our take on data sovereignty in 2026.

The local server is open source under Apache-2.0, and every release is published to npm with provenance attestation — cryptographic proof that the package you install was built from the public repository. Inspect it, audit it, fork it: github.com/American-Cloud/americancloud-mcp.

What can the American Cloud MCP server manage?

The server ships 179 tools in seven service groups, covering the American Cloud platform:

The hosted server lists every group. The local server loads compute, storage, networking and Kubernetes by default, and the --services flag adds databases, WordPress and DNS, so you only carry the tools you use. Cost-estimate tools are included throughout, so your assistant can answer "what would a 3-node Kubernetes cluster cost?" before anything gets created.

What can the assistant change?

We know what you're thinking: an AI with access to my production infrastructure?

That's why you decide what it can change, and the American Cloud API enforces that decision on every call:

• On the hosted server, each app gets its own permissions. A known app such as Claude, ChatGPT, Codex or Cursor starts with full access as you. An app that registered itself, such as Grok, starts read-only. In Connected apps you can set any app to Read-only, Full access or Custom at any time, and the app picks up the change on its next request. Revoke ends its access at once.
• The local server is read-only by default. Only read tools — list, inspect, cost estimates — are registered until you add the --allow-writes flag.
• A read-only token makes it a guarantee. Give the local server a token with the Read-only preset and writes are impossible at the account level, whatever the flag says. Let your AI audit everything; it cannot break anything.
• Changes are flagged. Every tool that changes or removes an existing resource carries a destructive marker, so MCP clients that support confirmations ask you first.

How do you connect Claude, Cursor or Codex?

Setup takes about a minute. For the hosted server, add https://mcp.americancloud.com/mcp as a connector or remote MCP server in your client, sign in to American Cloud, and ask: "What regions can I deploy to?"

For the local server, add this to your MCP client's configuration:

{
  "mcpServers": {
    "americancloud": {
      "command": "npx",
      "args": ["-y", "@americancloud/mcp"],
      "env": {
        "AMERICANCLOUD_API_TOKEN": "your-api-token"
      }
    }
  }
}

Create an API token (start with the Read-only preset) in the console and restart your client. This configuration is read-only. When you want the assistant to create and change resources, use a token with Full access and add the flag:

"args": ["-y", "@americancloud/mcp", "--allow-writes"]

We've written step-by-step guides for each client:

• Overview and quick start
• Claude.ai and Claude Desktop
• Claude Code
• Grok
• ChatGPT
• Cursor
• Codex
• Windsurf, VS Code, and other clients
• Things to try

What people are doing with it

A few patterns that emerged immediately in our own use:

The infrastructure audit. Connect with read-only permissions and ask the assistant to review everything: what's running, what it costs, which firewall rules are wider than they need to be, which volumes aren't attached to anything. Twenty minutes of conversation replaces an afternoon of clicking.

Incident triage. "Why can't I reach my app?" The assistant checks the VM's power state, walks the firewall rules, verifies port forwarding, and inspects load balancer membership — in one conversation, while you drink your coffee.

Cost-aware provisioning. Because cost estimates are tools too, the assistant can price out infrastructure before creating it: "Compare the monthly cost of one large VM versus three small ones behind a load balancer."

Build and deploy in one session. This is our favorite. In a coding agent like Claude Code, with write access turned on, the assistant can write your application and stand up the infrastructure to run it — create the VM, configure the firewall, point DNS at it, then deploy over SSH. Code and cloud in the same conversation.

Part of a bigger story

The MCP server sits alongside our official TypeScript, Go, and Python SDKs and our Terraform provider, all built on the American Cloud Platform API. Whether your operator is a human with a terminal, a CI pipeline, or an AI assistant, American Cloud is built to be driven programmatically. For how other clouds' MCP servers compare on where they run and what they can change, see which cloud providers have an MCP server.

Get started

1. Add https://mcp.americancloud.com/mcp to your client and sign in, or create an API token for the local server — start with the Read-only preset
2. Follow the setup guide for your client
3. Ask your assistant: "What's running in my account?"

Found a rough edge or want a tool we don't have yet? Open an issue — the server is open source and we're actively expanding it.