paddle

This MCP server exposes Paddle Billing tooling to LLMs and AI agents through a standardized MCP interface. It provides a comprehensive set of tools to manage your Paddle catalog, customers, subscriptions, payments, invoices, and more directly from conversations. The available tool groups cover Products, Prices, Discounts, Discount Groups, Customers, Addresses, Businesses, Transactions, Adjustments, Subscriptions, Saved Payment Methods, Customer Portal Sessions, Notification Settings, and Events, with each operation indicating whether it is non-destructive or read-only. You can invoke these tools to list, create, update, or retrieve Paddle data, and even preview or generate invoices and reports from within an AI workflow. The server is designed to mirror Paddle API capabilities so that assistants can perform end-to-end billing workflows in natural language or structured prompts.

Prerequisites:

• Node.js installed on your machine (recommended LTS version)
• Internet access to fetch packages via npx

Installation steps:

1. Ensure you have an API key for Paddle and decide the environment (sandbox or production). Set the environment variables accordingly.

2. Start the MCP server using the npx-based command from the README configuration:

   npx -y @paddle/paddle-mcp

   This will pull the Paddle MCP server package and launch the server, wiring up the Paddle API with the MCP tools.

3. If you want to customize environment variables or run in a container, configure the mcp_config section accordingly (see the generated documentation for details).

4. Verify the server is running by checking the console output or using the MCP discovery/health checks provided by your integration environment.

Tips and caveats:

• Use PADDLE_API_KEY with caution; treat it like a secret key and rotate it as needed.
• PADDLE_ENVIRONMENT should be sandbox for development and testing, switching to production when ready.
• PADDLE_MCP_TOOLS can be set to non-destructive to limit the actions during initial exploration; switch to full access once you’re comfortable.
• The tools mirror Paddle API capabilities; refer to Paddle’s API docs for details on each operation’s parameters and behavior.
• If you encounter rate limits or authentication errors, verify that the API key is active and has the necessary permissions for the requested operations.
• For local development, ensure network access to Paddle’s endpoints and that any required webhooks or callback URLs are reachable by Paddle if applicable.