Skip to content
Create account or Sign in
The Stripe Docs logo
/
Create accountSign in

Build on Stripe with LLMs

Use LLMs in your Stripe integration workflow.

You can use large language models (LLMs) to assist in the building of Stripe integrations. We provide a set of tools and best practices if you use LLMs during development.

Model Context Protocol (MCP)

Stripe Model Context Protocol (MCP) defines a set of tools that AI agents can use to interact with the Stripe API and search our knowledge base, including documentation and support articles. As you work with an agent, it can use these tools to answer questions and complete tasks in your Stripe account directly from your LLM.

If you’re using an agent to help build or operate your Stripe integration, connect it to our MCP server.

Use agent skills

Agent skills give LLMs task-specific instructions. Stripe offers several skills, including:

How you add skills depends on the platform. Use the following instructions for each platform:

Use AI developer platforms

Agent-assisted coding platforms let you create apps and websites by describing what you want to an LLM. These platforms can also help you build a payments integration without writing code.

Some platforms, such as Base44, Manus, Replit, and v0, provide custom Stripe integrations so you can try Stripe without creating an account. If you’re building an agent-assisted developer platform, you can offer a similar experience with claimable sandboxes.

Plain text docs

You can access all of our documentation as plain text markdown files by adding .md to the end of any url. For example, you can find the plain text version of this page itself at https://docs.stripe.com/building-with-llms.md.

This helps AI tools and agents consume our content and allows you to copy and paste the entire contents of a doc into an LLM. This format is preferable to scraping or copying from our HTML and JavaScript-rendered pages because:

  • Plain text contains fewer formatting tokens.
  • Content that isn’t rendered in the default view (for example, it’s hidden in a tab) of a given page is rendered in the plain text version.
  • LLMs can parse and understand markdown hierarchy.

We also host an /llms.txt file which instructs AI tools and agents how to retrieve the plain text versions of our pages. The /llms.txt file is an emerging standard for making websites and content more accessible to LLMs.

VS Code AI Assistant

If you’re a Visual Studio Code user, you can install the Stripe VS Code extension to access our AI Assistant.

With the Stripe AI Assistant, you can:

  • Get immediate answers about the Stripe API and products
  • Receive code suggestions tailored to your integration
  • Ask follow-up questions for more detailed information
  • Access knowledge from the Stripe documentation and the Stripe developer community

To get started with the Stripe AI assistant:

  1. Make sure you have the Stripe VS Code extension installed.
  2. Navigate to the Stripe extension UI
  3. Under AI Assistant click Ask a question.
    • If you’re a Copilot user, this opens the Copilot chat where you can @-mention @stripe. In the input field, talk to the Stripe-specific assistant using @stripe followed by your question.
    • If you’re not a Copilot user, it opens a chat UI where you can talk to the Stripe LLM directly.

Stripe Agent Toolkit SDK

If you’re building agentic software, we provide an SDK for adding Stripe functionality to your agent’s capabilities. For example, using the SDK you can:

  • Create Stripe objects
  • Charge for agent usage
  • Use with popular frameworks such as OpenAI’s Agent SDK, Vercel’s AI SDK, Langchain, and CrewAI

Learn more about agents.

See also