Paddle MCP Server

Give any AI assistant direct access to the Paddle API over the Model Context Protocol.

This server gives AI assistants like Claude, Cursor, and Windsurf direct access to Paddle API operations — products, prices, subscriptions, customers, transactions, and more.

Three tools are exposed to your assistant: search the API reference, execute chained API calls in a sandbox, and report_missing_tool for telemetry.

01

Endpoint

A single MCP endpoint. Each host serves one environment — connect to sandbox-mcp.paddle.com for sandbox and mcp.paddle.com for live.

POST https://sandbox-mcp.paddle.com/mcp
02

Authentication

Sandbox connects with a sandbox API key (prefixed pdl_sdbx_), passed in the Authorization header on every request. The sandbox server doesn't support OAuth — on mcp.paddle.com you can sign in with OAuth instead.

HTTP header 
Authorization: Bearer <your-sandbox-api-key>

Scope the key to the permissions you actually need — they are the only limit on what the assistant can do.

03

Connect Your Client

Drop one of these configurations into your AI client. Replace API_KEY with your own key.

/terminal 
claude mcp add --transport http paddle https://sandbox-mcp.paddle.com/mcp --header "Authorization: Bearer API_KEY"

For more detailed setup instructions, see the full installation guide.