Lemon Squeezy MCP Server

Lemon Squeezy MCP Server

📖 About

Give your AI assistant direct access to your payment and subscription data.

This server acts as a bridge between your AI assistant (like VS Code, Claude Desktop, or any MCP-compatible client) and your Lemon Squeezy account. Instead of manually logging into dashboards, searching for orders, and copy-pasting details, you can simply ask your AI questions like:

• "What was the last sale?"
• "Is subscription #12345 still active?"
• "Find all customers named 'Alice'"

Your AI will query the data securely and give you an instant answer, right in your code editor.

🌱 Beginner Level: Getting Started

Who is this for? You are new to CLI tools or just want to get this running quickly with minimal fuss.

1. Prerequisites

Before you start, make sure you have these two things installed on your computer:

• Node.js (Version 18 or higher): This is the software that runs the server. Download Node.js here.
• A Lemon Squeezy Account: You need an account to get the data. Sign up here.

2. Get Your API Key

Think of this as your password for the server.

1. Log in to your Lemon Squeezy Dashboard.
2. Go to Settings -> API.
3. Click Create API Key.
4. Copy the key (it starts with ls_...). Keep this safe!

3. Quick Installation

Open your terminal (Command Prompt on Windows, Terminal on Mac) and run these commands one by one:

# 1. Download the project
git clone https://github.com/IntrepidServicesLLC/lemonsqueezy-mcp-server.git
cd lemonsqueezy-mcp-server

# 2. Install the necessary files
npm install

# 3. Build the server
npm run build

4. Connect to Your AI Editor

The exact steps depend on which AI editor you're using. Here are the most common:

One-copy-paste setup (Claude Desktop / Cursor / npx):
Add this to your MCP config file (e.g. claude_desktop_config.json or Cursor MCP settings). Replace YOUR_KEY_HERE with your Lemon Squeezy API key.

"mcpServers": {
  "lemonsqueezy": {
    "command": "npx",
    "args": ["-y", "lemonsqueezy-mcp-server"],
    "env": {
      "LEMONSQUEEZY_API_KEY": "YOUR_KEY_HERE"
    }
  }
}

(Requires the package to be published on npm. For local development, use the path-based config below.)

For VS Code (local path):

1. Open VS Code Settings
2. Go to Extensions → MCP
3. Add a new MCP server with:
   • Command: node
   • Args: ["/absolute/path/to/lemonsqueezy-mcp-server/dist/index.js"]
   • Env: {"LEMONSQUEEZY_API_KEY": "your_api_key_here"}

For Claude Desktop (local path):

1. Edit ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
2. Add the same configuration as above (command node, args with full path to dist/index.js)
3. Restart Claude Desktop

For Other MCP Clients: Refer to your client's documentation for adding MCP servers. The server runs via node /path/to/dist/index.js with the LEMONSQUEEZY_API_KEY environment variable set.

After configuring, restart your AI editor and try asking: "Show me my last 5 orders."

🚀 Medium User Level: Basic Usage & Configuration

Who is this for? You are comfortable with config files, environment variables, and want to customize how the server works.

Philosophy: "Sensible Defaults"

This server is designed to work out of the box with just one required setting: your LEMONSQUEEZY_API_KEY. Everything else is optional and has pre-configured defaults that work for 90% of users.

Configuration Options

You can configure the server using Environment Variables in your MCP settings or a .env file.

Common Tasks

1. Using Test Mode If you want to develop without touching real money, generate a "Test API Key" in Lemon Squeezy and use LEMONSQUEEZY_TEST_API_KEY. The server will automatically prioritize the live key if both are present, so remove the live key to force test mode.

2. Enabling Salesforce Integration (Bonus) Want to sync customers to your CRM? Add these variables:

• SALESFORCE_USERNAME
• SALESFORCE_PASSWORD
• SALESFORCE_TOKEN (Security Token)

The tools for Salesforce (like sync_customer_to_crm) will automatically appear in your AI's toolkit.

Troubleshooting

• **"Command not found"