Paddle MCP Server

MCP Server for Paddle Billing

Local serverstdio

What is the Paddle MCP server?

Most payments and commerce work still happens through a UI a human drives. Paddle MCP server moves it into the conversation instead. MCP Server for Paddle Billing.

The short version

Paddle Billing is the developer-first merchant of record. We take care of payments, tax, subscriptions, and metrics with one unified API that does it all.

  • Manage your full Paddle catalog
  • View customer, purchase, and provisioning information
  • Handle subscription, payment, and refund workflows
  • Debug billing and order management issues
  • Create and adjust transactions directly in conversation
  • Generate financial reports for financial and operational insights

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

The tools it exposes

The server publishes 4 tools. What each one is for:

  • all — All tools are available
  • read-only — Only read operations are available
  • non-destructive — Read operations and safe write operations are available (default)
  • Operation — Tool

What it needs from you

Configuration is passed through the environment: PADDLE_API_KEY, PADDLE_ENVIRONMENT, PADDLE_MCP_TOOLS. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the payments and commerce options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Paddle's toolset — all, read-only, non-destructive and 1 more — is a fair guide to whether it matches your workflow. It is maintained by PaddleHQ; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Paddle's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
allAll tools are available
read-onlyOnly read operations are available
non-destructiveRead operations and safe write operations are available (default)
OperationTool

How to install the Paddle MCP server

{
  "mcpServers": {
    "paddle": {
      "command": "npx",
      "args": [
        "-y",
        "@paddle/paddle-mcp",
        "--api-key=your_api_key",
        "--environment=sandbox",
        "--tools=non-destructive"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
PADDLE_API_KEYCredential the server authenticates with.Yes
PADDLE_ENVIRONMENTConfiguration value read at startup.Optional
PADDLE_MCP_TOOLSConfiguration value read at startup.Optional

Example prompts to try

  • Use Paddle to all.
  • Use Paddle to read-only.
  • Use Paddle to non-destructive.

Frequently asked questions

It connects Paddle to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (all, read-only, non-destructive, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Paddle directly.