Complete AI Training

MCP server · Developer tools

Terraform MCP server

by RajeevSirohi

Ask your AI to run Terraform plans, apply changes and check your cloud infrastructure in plain words.

Flow diagram: you ask your AI “Plan the changes in my staging folder and explain them”, on your own computer the Terraform MCP server works with terraform, and you get back plain summary of changes.

This is a small helper that connects your AI assistant to Terraform, the tool many teams use to set up and manage cloud infrastructure. Once it is connected, you can ask for a plan, review what will change, and apply it without switching to a terminal. It is handy for anyone who runs Terraform but does not want to memorise every command.

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 Terraform on your own computer, so it can run real Terraform commands for you when you ask. You stay in the conversation, and the helper does the typing.

What this MCP server does

You ask your AI something like "plan the changes in my staging folder and explain them". The AI passes that request to this helper, which runs the real terraform command on your machine. The helper reads the result, adds a short summary with counts and cost warnings, and hands it back. Your AI then explains it to you in plain words. For anything that changes or deletes infrastructure, the helper asks for a second confirmation before it acts.

Flow diagram: you ask your AI “Plan the changes in my staging folder and explain them”, on your own computer the Terraform MCP server works with terraform, and you get back plain summary of changes. Click to zoom

What you can do with it

  • Run a plan and see what would be created, changed or destroyed
  • Apply changes only after you confirm the plan
  • Destroy infrastructure with a two-step safety check
  • Read outputs and list what is in your state file
  • Detect resources that were changed outside Terraform
  • Import existing cloud resources into Terraform state
  • Flag expensive always-on resources with rough monthly costs

Try asking your AI

  • “Plan the changes in my staging folder and explain what will change”
  • “Apply it, but only if nothing will be destroyed”
  • “Show me all the outputs from the prod workspace”
  • “Did anyone change anything outside Terraform in the prod workspace?”

What it gives back to you

You get back a readable summary in the chat: how many resources would be created, updated or destroyed, which ones are destructive, and warnings about costly resources with rough monthly prices. For outputs or state listings you get a simple list of names and values. When it changes something, it tells you what it did. If a plan fails, it can walk through a step-by-step diagnosis.

Before you start

What you need

  • Node.js 18 or newer on your computer
  • The Terraform command line tool installed and on your PATH
  • The Claude desktop app or another app that supports MCP
  • Cloud login already set up for the provider you use (for example aws configure or az login)

Good to know

It can really create, change and delete your cloud infrastructure and can cost money, so always read the plan before you confirm an apply or destroy.

Install it with your AI

Add Terraform 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 Terraform 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.

Sign in Become a member

Who it's for

People who already use Terraform for cloud infrastructure and want to run plans, applies and checks by talking instead of typing commands.