Firefly MCP

Firefly MCP

What is Firefly MCP about?

A TypeScript‑based server that connects to the Firefly platform to discover resources across cloud and SaaS accounts, convert those resources into Infrastructure‑as‑Code (IaC) definitions, and expose them through a Model Context Protocol endpoint.

How to use Firefly MCP?

1. Ensure Node.js (v14+) is installed.
2. Run the server directly with NPX:

   npx @fireflyai/firefly-mcp
   

3. Provide credentials either via environment variables:

   FIREFLY_ACCESS_KEY=your_access_key FIREFLY_SECRET_KEY=your_secret_key npx @fireflyai/firefly-mcp
   

   or via command‑line arguments:

   npx @fireflyai/firefly-mcp --access-key your_access_key --secret-key your_secret_key
   

4. Start the server with SSE support (optional) and a custom port:

   npx @fireflyai/firefly-mcp --sse --port 6001
   

5. Configure mcp.json to point your client (e.g., Cursor) at the running endpoint.

Key features of Firefly MCP

• 🔍 Resource discovery across multiple cloud and SaaS providers.
• 📝 Automatic conversion of discovered resources into IaC (Terraform, etc.).
• 🔐 Secure authentication using FIREFLY_ACCESS_KEY and FIREFLY_SECRET_KEY.
• 🚀 Simple execution via NPX with no global installation required.
• 🤝 Seamless integration with AI assistants like Claude and IDE extensions such as Cursor.

Use cases of Firefly MCP

• Quickly generate Terraform code for existing cloud resources.
• Enable developers to query infrastructure using natural language within their IDE.
• Automate inventory management for multi‑account cloud environments.
• Provide a centralized context source for AI‑driven code assistants.

FAQ

• Do I need to install anything globally? No. The server runs via NPX, which downloads the package on demand.
• Which cloud providers are supported? Any provider that can be accessed with the Firefly platform credentials (e.g., AWS, Azure, GCP, plus supported SaaS services).
• Can I run the server behind a firewall? Yes. The server binds to the specified port (default 6001) and can be accessed via the configured URL in mcp.json.
• How is authentication handled? By setting FIREFLY_ACCESS_KEY and FIREFLY_SECRET_KEY either in the environment or via CLI arguments.
• Is the output limited to Terraform? The primary example uses Terraform, but the underlying codification engine can be extended to other IaC formats.

Firefly MCP Server

The Firefly MCP (Model Context Protocol) server is a TypeScript-based server that enables seamless integration with the Firefly platform. It allows you to discover, manage, and codify resources across your Cloud and SaaS accounts connected to Firefly.

Features

• 🔍 Resource Discovery: Find any resource in your Cloud and SaaS accounts
• 📝 Resource Codification: Convert discovered resources into Infrastructure as Code
• 🔐 Secure Authentication: Uses FIREFLY_ACCESS_KEY and FIREFLY_SECRET_KEY for secure communication
• 🚀 Easy Integration: Works seamlessly with Claude and Cursor

Prerequisites

• Node.js (v14 or higher)
• npm or yarn
• Firefly account with generated access keys

Installation

You can run the Firefly MCP server directly using NPX:

npx @fireflyai/firefly-mcp

Environment Variables

You can provide your Firefly credentials in two ways:

1. Using environment variables:

FIREFLY_ACCESS_KEY=your_access_key FIREFLY_SECRET_KEY=your_secret_key npx @fireflyai/firefly-mcp

2. Using arguments:

npx @fireflyai/firefly-mcp --access-key your_access_key --secret-key your_secret_key

Usage

Stdio

Update the mcp.json file with the following:

{
  "mcpServers": {
    "firefly": {
      "command": "npx",
      "args": ["-y", "@fireflyai/firefly-mcp"],
      "env": {
        "FIREFLY_ACCESS_KEY": "your_access_key",
        "FIREFLY_SECRET_KEY": "your_secret_key"
      }
    }
  }
}

Run the MCP server using one of the methods above with the following command:

npx @fireflyai/firefly-mcp --sse --port 6001

Update the mcp.json file with the following:

{
  "mcpServers": {
    "firefly": {
      "url": "http://localhost:6001/sse"
    }
  }
}

Using with Cursor

1. Start the MCP server using one of the methods above
2. Use the Cursor extension to connect to the MCP server - see Cursor Model Context Protocol documentation
3. Use natural language to query your resources

Example:

Prompt

Find all "ubuntu-prod" EC2 instance in 123456789012 AWS account and codify it into Terraform

Response

resource "aws_instance" "ubuntu-prod" {
  ami           = "ami-0c55b159cbfafe1f0"
  instance_type = "t3.micro"
}

Demo

https://github.com/user-attachments/assets/0986dff5-d433-4d82-9564-876b8215b61e

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'feat: Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For support, please visit Firefly's documentation or create an issue in this repository.