MCP server · Developer tools

Cloudwright MCP server

Turn a plain-English cloud idea into a cost estimate, a compliance check and ready-to-use infrastructure code.

Developer tools For it and development Cloud Platforms

Cloudwright is a helper that takes one sentence about the cloud setup you want and turns it into a written plan, a cost breakdown, a compliance report and infrastructure code. It works with AWS, Google Cloud, Azure and Databricks. It is handy if you plan cloud setups, review them, or need to show costs and rules before anything gets built.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. This one connects your AI to Cloudwright, so when you ask for a cloud design, your AI can call Cloudwright behind the scenes. Cloudwright then does the real work and hands the results back to your AI, which explains them to you in the chat.

What this MCP server does

You describe the cloud setup you want in everyday words, like a healthcare API on AWS with a database and a cache. Your AI passes that to Cloudwright through this MCP server. Cloudwright writes a structured plan, prices each piece, checks it against rules like HIPAA or SOC 2, and can produce infrastructure code such as Terraform. Your AI then shows you the plan, the numbers and the findings right in the chat. It can also plan a migration from an old setup to a new one, but it never actually copies data or changes anything live.

Flow diagram: you ask your AI “Design a HIPAA healthcare API on AWS with Postgres and Redis”, the Cloudwright MCP server works in steps: write a plan, then price and check, then make code files, and you get back plan, costs, checks and code.

Click to zoom

What you can do with it

Design a cloud setup from a one-line description
Estimate monthly costs per component and per region
Check a design against HIPAA, SOC 2, PCI-DSS and other frameworks
Export infrastructure code as Terraform, Pulumi or CloudFormation
Draw a simple diagram of the setup
Plan a migration in ordered waves and check the evidence
Review a design for weak spots and single points of failure

Try asking your AI

“Design a HIPAA healthcare API on AWS with Postgres and Redis”
“What would this setup cost per month in the EU region”
“Check this design against SOC 2 and list any issues”
“Export this design as Terraform code”

What it gives back to you

You get back a written plan in a structured format, a cost breakdown per component, a list of compliance findings with the rule each one relates to, and code files you can save. Diagrams can come back as plain text or a simple drawing format. Everything shows up in the chat as text you can read, copy or download.

Before you start

What you need

Python 3.12 or newer
An Anthropic or OpenAI API key (a kind of password for the AI service; you get one from their website)
The cloudwright-ai package installed, for example with pip install 'cloudwright-ai[cli]'

Good to know

It can write files and infrastructure code for you, so review the output before you use it, and remember it never applies changes or moves data on its own.

Install it with your AI

Add Cloudwright MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Cloudwright MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.