For AI agents and LLMs: a structured documentation index is available at /llms.txt. Every page has a Markdown sibling — append .md to any URL.

Skip to content
Docs

Agents and AI

MCP servers, Agent Skills, and embedded docs AI — tools that let AI agents integrate, operate, and reason about Paddle.

AI summary

Connect AI agents like Claude and Cursor directly to Paddle so they can execute billing operations, debug issues, and integrate Paddle features through natural language. Paddle ships two MCP servers — one for taking actions in your account, one for up-to-date Paddle knowledge.

  • • Paddle exposes two MCP servers: the Paddle MCP server (local) for reading data and taking actions in your account, and the docs MCP server (remote) for current Paddle documentation knowledge.
  • • Use both MCP servers together so the docs server explains how Paddle works and the Paddle server actually performs operations against your account.
  • • Every page in the docs is available as Markdown by appending .md to the URL or clicking 'Copy for LLM'; AI clients are auto-served Markdown to preserve tokens, and /llms.txt indexes every page.

Connect AI agents like Claude and Cursor directly to Paddle to work through complex flows in seconds. Build pricing models, investigate failed payments, integrate Paddle features, or process customer refunds — all in natural language.

AI tools

Paddle MCP server (local)

Lets AI agents read data and take actions in your Paddle account.

Docs MCP server (remote)

Give AI agents full up-to-date knowledge of Paddle.

Agent skills

Drop-in instructions that teach coding agents how to integrate Paddle correctly.

Use them together. The docs MCP server tells the agent how Paddle works; the Paddle MCP server lets it take actions in your account; Agent Skills give coding agents the step-by-step patterns they need to write correct Paddle integration code.

Use cases

Combine the Paddle MCP server with the docs MCP server to:

  • Integrate Paddle
    Use Agent Skills to give your coding agent step-by-step instructions for checkout, webhooks, subscription sync, and more — then use the Paddle MCP server to create the catalog and test the result.
  • Build and evolve your pricing
    Create complete pricing models or catalogs with regional variations by describing your structure.
  • Investigate billing issues
    Ask about specific customer problems and get complete transaction and subscription histories with explanations.
  • Onboard enterprise customers
    Migrate and set up enterprise customers with custom pricing and manual invoicing. Use in conjunction with quote management tools and CRMs.
  • Handle subscription changes
    Process subscription changes and transaction adjustments intelligently with context, recommendation, and action.
  • Analyze company performance
    Generate custom reports and get insights about revenue, churn, and customer behavior.

Integration experience

You describe what you need

Ask your AI agent about billing operations, customer issues, integration tasks, or anything Paddle-related. Describe what you're trying to achieve in plain language.

Assistant identifies tools to use

The agent selects which tools it needs to fulfill your request. There can be multiple.

It may ask follow-up questions to clarify, gather required details, or better understand your goal.

You review before actions execute

Most agents verify their actions before accessing data or making changes to your account.

You can approve, request changes, or ask questions. Nothing happens without your confirmation by default.

Assistant executes and explains

Products get created, issues get resolved, code gets written, or reports get generated. The agent explains the results and provides insights when relevant.

The full context is maintained, so you can ask follow-up questions, request adjustments, or work through complex scenarios without starting over.

Ask AI in the docs

Click Ask AI on any page to open the agent embedded in the docs. Two modes:

  • Fast: quick questions about concepts, API behavior, and how Paddle works.
  • Thinking: detailed explanations or working through a specific integration problem.

llms.txt

The /llms.txt file is a plain-text index of every page in these docs. AI clients can use it to find Paddle content without parsing HTML.

Get content as Markdown

Every page in the docs is available as Markdown:

  • Append .md to any doc URL to fetch the raw source, for example https://developer.paddle.com/sdks/ai.md
  • Click Copy for LLM on every page to copy the Markdown directly to your clipboard.

When AI agents browse the documentation, we automatically serve them the Markdown version of the page to preserve tokens.

Was this page helpful?