Build Paddle integrations faster with the Paddle Docs MCP server

What's new?

We've released the Paddle Docs MCP server, a hosted Model Context Protocol (MCP) server that gives your AI assistant up-to-date knowledge of the entire Paddle platform. Install it everywhere you use AI so your conversations in clients and IDEs immediately draw on up-to-date Paddle knowledge.

The Paddle Docs MCP server gives AI assistants knowledge of the Paddle platform. It doesn't access or modify your Paddle account data. To let AI assistants take actions in your account like creating catalog items, setting up notification destinations, or managing subscriptions, set up the Paddle MCP server.

How it works

AI assistants are only as good as what they know. Without access to the latest documentation, they can give outdated advice, miss important details, or confidently suggest things that are no longer accurate.

Model Context Protocol (MCP) is an open standard that lets AI assistants query live external sources during a conversation, rather than relying entirely on what they learned during training. With the Paddle Docs MCP server installed, your AI assistant retrieves current Paddle content in real time whenever it needs to respond to a Paddle-related question. Answers are grounded in current documentation rather than whatever was indexed at training time.

The biggest gains are in AI-powered IDEs, like Cursor, VS Code, or Claude Code, where your assistant already has context about your codebase. You can ask it to write a webhook handler, explain what a transaction status means in the context of your provisioning logic, or review your subscription management functionality against the latest API spec - and it'll draw on both your code and live Paddle content to respond.

Once a feature is implemented, your assistant can interpret anything that went wrong, check the current Paddle documentation for the correct behavior or fix, apply it, and validate again. Each step uses live content rather than training data, so it stays accurate even when Paddle has changed since the model was trained.

We recommend installing it in every AI tool you use. The more places it's connected, the less time you'll spend second-guessing suggestions or cross-referencing documentation manually.

You only need to install it once per AI tool. The server runs in the background and performs searches automatically with no extra instruction required. Most clients show a visible indicator when a search is in progress. If you notice the assistant falling back on training data, you can explicitly prompt it to check the current Paddle documentation.

On first use, you may be asked to authenticate with Kapa.ai using your Google account. This confirms the request is legitimate and keeps the service reliable for everyone.

Quick install

Cursor

VS Code

Claude Code

OpenAI Codex

Raycast

Other

Examples

1
1Using the latest Paddle documentation, what's the correct way to verify a webhook signature with my current Node.js implementation?

1
1Check the Paddle docs and tell me which fields I need to include when creating a one-time charge on an existing subscription.

1
1Looking at the current Paddle documentation, what are the most likely causes of a `too_many_requests` error when calling the transactions endpoint, and how should I handle it?

1
1Based on the current Paddle docs, what are the main differences between Paddle Classic and Paddle Billing, and what would I need to update in my existing integration to migrate?

1
1Searching the Paddle documentation, give me detailed instructions on how to open a customer portal for my customers to manage their subscriptions.

1
1Check the Paddle docs. What's the difference between Paddle Classic and Paddle Billing?

Next steps

The Paddle Docs MCP server is available now.

Installation takes a few minutes and varies slightly by AI client. For step-by-step instructions covering Claude Desktop, Claude Code, Cursor, VS Code, and other MCP-compatible tools, see Give AI assistants up-to-date Paddle knowledge.

We recommend installing it in every AI assistant you use regularly for Paddle development to avoid guesswork and get accurate answers.

Related pages