Firefly MCP server

Bridges to Firefly.ai's cloud infrastructure platform, enabling inventory queries across providers and Terraform code generation for discovered resources.
Back to servers
Setup instructions
Provider
Firefly.io
Release date
Mar 31, 2025
Language
TypeScript
Package
Stats
2.0K downloads
12 stars

The Firefly MCP (Model Context Protocol) server enables seamless integration with the Firefly platform, allowing you to discover, manage, and codify resources across your Cloud and SaaS accounts connected to Firefly. It helps you find resources and convert them into Infrastructure as Code with natural language queries.

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

Authentication Setup

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
  1. Using command-line arguments:
npx @fireflyai/firefly-mcp --access-key your_access_key --secret-key your_secret_key

Usage

Setting Up with Stdio

Add the following to your mcp.json file:

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

Server-Sent Events (SSE) Mode

To run the MCP server in SSE mode:

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

Then update your mcp.json file:

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

Integration with Cursor

  1. Start the MCP server using one of the methods above
  2. Connect to the MCP server using the Cursor extension
  3. Use natural language to query your resources

Example Query

Here's an example of how you might use the Firefly MCP server:

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"
}

Key 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
  • Easy Integration: Works with Claude and Cursor

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

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

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

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

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later