Firefly Mcp

What is Firefly Mcp about?

Enables seamless integration with the Firefly platform to discover any resource in connected cloud and SaaS accounts and convert those resources into Infrastructure‑as‑Code definitions.

How to use Firefly Mcp?

1. Installation – Run the server directly with NPX:

   npx @fireflyai/firefly-mcp
   

2. 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
   

3. Start the server (example for SSE on port 6001):

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

4. Configure MCP client (e.g., in mcp.json):

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

5. Query resources using natural language through supported tools such as Cursor.

Key Features

• Resource Discovery – Locate any cloud or SaaS asset linked to a Firefly account.
• Resource Codification – Generate Terraform (or other IaC) code from discovered resources.
• Secure Authentication – Uses FIREFLY_ACCESS_KEY and FIREFLY_SECRET_KEY.
• Easy Integration – Works out‑of‑the‑box with Claude, Cursor, and any MCP‑compatible client.
• Zero‑install option – Run via npx without pre‑installing the package.

Use Cases

• Infrastructure‑as‑Code generation – Turn existing cloud resources into Terraform scripts for version control.
• Dynamic inventory for AI assistants – Allow agents like Claude or Cursor to query live cloud state.
• Multi‑cloud visibility – Consolidate resources from AWS, GCP, Azure, and SaaS apps into a single queryable model.
• Compliance and audit – Quickly list resources and export their configurations for review.

FAQ

Q: Do I need to install Node.js globally? A: Only a compatible Node.js runtime (v14+) is required; the server runs via npx.

Q: Can I run the server on a remote host? A: Yes, start it on any machine reachable by your client and point the url field in mcp.json to that host.

Q: Which IaC formats are supported? A: Currently Terraform is demonstrated; additional formats can be added via Firefly extensions.

Q: How are credentials kept secure? A: Pass them as environment variables or use a secrets manager; they are never stored in code.

Q: Is there a Docker image? A: Not provided in the README, but you can containerize the npx command if needed.

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.