Building 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.

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.

Stripe Model Context Protocol (MCP) Server

For developers using code editors that use AI, such as Cursor or Windsurf, or general purpose tools such as Claude Desktop, we provide the Stripe Model Context Protocol (MCP) server. The MCP server provides AI agents a set of tools for calling the Stripe API and searching our knowledge base (documentation, support articles, and so on).

CLI

Run the following command to start the MCP server locally.

Command Line
npx -y @stripe/mcp --tools=all --api-key=sk_test_BQokikJOvBiI2HlWgH4olfQ2

Cursor

Add the following to your .cursor/mcp.json file. Go to Cursor Settings > MCP and make sure the server is enabled and the selected tools are available. See the Cursor documentation for more details.

{
  "mcpServers": {
    "stripe": {
      "command": "npx",
      "args": [
          "-y",
          "@stripe/mcp",
          "--tools=all",
          "--api-key=sk_test_BQokikJOvBiI2HlWgH4olfQ2"
      ]
    }
  }
}

Claude Desktop

Add the following to your claude_desktop_config.json file. See the Claude Desktop documentation for more details.

{
  "mcpServers": {
    "stripe": {
      "command": "npx",
      "args": [
          "-y",
          "@stripe/mcp",
          "--tools=all",
          "--api-key=sk_test_BQokikJOvBiI2HlWgH4olfQ2"
      ]
    }
  }
}

The code editor agent automatically detects all the available tools and calls the relevant tool when you post a related question in the chat.

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:

Make sure you have the Stripe VS Code extension installed.
Navigate to the Stripe extension UI
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 in our agents documentation.

注