Complete AI Training

MCP server · Developer tools · official

Firefly MCP server

by gofireflyio · official

Lets your AI find cloud and SaaS resources in Firefly and turn them into infrastructure code.

Flow diagram: you ask your AI “Find my ubuntu-prod servers in AWS”, the Firefly MCP server connects it to Firefly, and you get back A list of matching resources.

This is a small helper that connects your AI assistant to Firefly, a service that keeps track of the cloud and software accounts your company uses. Once it is set up, you can ask your AI in plain words to find a resource or write it out as code. It is handy for people who work with cloud infrastructure, even if they are not deep experts.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you using what it already knows. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to Firefly, so it can look things up in your connected cloud and SaaS accounts and do things there when you ask. You stay in the chat, and the helper does the talking to Firefly behind the scenes.

What this MCP server does

You ask your AI something like finding a specific server in one of your cloud accounts. The AI passes your request to this helper, and the helper talks to Firefly using your access keys. Firefly looks across the cloud and SaaS accounts you have connected to it and finds matching resources. The helper then brings the answer back, and if you asked for it, it can turn that resource into infrastructure code you can copy.

Flow diagram: you ask your AI “Find my ubuntu-prod servers in AWS”, the Firefly MCP server connects it to Firefly, and you get back A list of matching resources. Click to zoom

What you can do with it

  • Find resources across your connected cloud and SaaS accounts
  • Search for a specific resource by name or account
  • Turn a discovered resource into infrastructure code
  • Get a Terraform snippet for a resource you found
  • Ask questions about what is running in your accounts

Try asking your AI

  • “Find all ubuntu-prod EC2 instances in my AWS account 123456789012”
  • “Codify that EC2 instance into Terraform”
  • “What resources do I have in my Firefly account right now”
  • “Show me the Terraform code for the ubuntu-prod instance”

What it gives back to you

You get answers in the chat, usually as a short list of matching resources with their names and details. If you asked for code, you get a snippet you can copy, like a Terraform block for the resource. The helper does not change anything in your accounts by itself; it looks things up and writes code for you.

Before you start

What you need

  • A Firefly account
  • Access keys from Firefly (FIREFLY_ACCESS_KEY and FIREFLY_SECRET_KEY, which you generate in your Firefly account)
  • Node.js version 20 or newer on the machine running the helper
  • An AI app that supports MCP, like Claude or Cursor

Good to know

The keys you use give access to your Firefly account, so keep them private and only share them with the AI app you trust.

Install it with your AI

Add Firefly 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 Firefly 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

Cloud and platform engineers, DevOps people, and anyone who manages cloud resources and wants quick answers or Terraform code without clicking around.