Stripe AI

What is Stripe AI about?

Stripe AI offers a collection of SDKs that let developers connect Stripe’s payment and billing infrastructure to LLMs and agent platforms. It includes toolkits for Python and TypeScript, an AI SDK for Vercel’s ai ecosystem, and a token‑meter for usage‑based billing with OpenAI, Anthropic, and Google Gemini.

How to use Stripe AI?

• Install the desired package:
  • Python: pip install stripe-agent-toolkit
  • TypeScript: npm install @stripe/agent-toolkit
• Configure the toolkit with your Stripe secret key and optional configuration (actions, context, etc.).
• Pass the generated tools to your LLM or agent framework (OpenAI Agent SDK, LangChain, CrewAI, Vercel AI SDK, etc.) and invoke Stripe APIs via function calling.
• Optional: Run a local MCP server with npx -y @stripe/mcp --tools=all --api-key=YOUR_STRIPE_SECRET_KEY for secure remote access.

Key features of Stripe AI

• Unified SDKs for Python and TypeScript.
• Seamless function‑calling integration with popular agent frameworks.
• Token‑metering to bill LLM usage against Stripe billing.
• Built‑in support for connected‑account context.
• Ability to run a local Model Context Protocol server for OAuth‑protected access.

Use cases of Stripe AI

• Building AI assistants that can create payment links, invoices, or subscription plans on‑the‑fly.
• Monetizing custom LLM applications by charging per token usage through Stripe.
• Automating e‑commerce workflows where an LLM recommends products and directly processes checkout.
• Enabling SaaS platforms to expose AI‑driven features while handling billing, taxes, and compliance with Stripe.

FAQ from Stripe AI

Q: Do I need the source code to use the SDKs? A: No. Install the packages via pip or npm and import them directly.

Q: Which Python version is required? A: Python 3.11 or newer.

Q: What Node version is required? A: Node 18+.

Q: How do I provide a default connected account for API calls? A: Include a context object with an account field in the toolkit configuration.

Q: Can I run the MCP server locally? A: Yes, use the npx command shown above and supply your Stripe secret key.

Q: Where can I find the list of supported Stripe API methods? A: Refer to the Stripe MCP documentation at https://docs.stripe.com/mcp.

Stripe AI

This repo is the one-stop shop for building AI-powered products and businesses on top of Stripe.

It contains a collection of SDKs to help you integrate Stripe with LLMs and agent frameworks, including:

• @stripe/agent-toolkit - for integrating Stripe APIs with popular agent frameworks through function calling—available in Python and TypeScript.
• @stripe/ai-sdk - for integrating Stripe's billing infrastructure with Vercel's ai and @ai-sdk libraries.
• @stripe/token-meter - for integrating Stripe's billing infrastructure with native SDKs from OpenAI, Anthropic, and Google Gemini, without any framework dependencies.

Model Context Protocol (MCP)

Stripe hosts a remote MCP server at https://mcp.stripe.com. This allows secure MCP client access via OAuth. View the docs here.

The Stripe Agent Toolkit also exposes tools in the Model Context Protocol (MCP) format. Or, to run a local Stripe MCP server using npx, use the following command:

npx -y @stripe/mcp --tools=all --api-key=YOUR_STRIPE_SECRET_KEY

See MCP for more details.

Agent toolkit

Stripe's Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, CrewAI, and Vercel's AI SDK to integrate with Stripe APIs through function calling. The library is not exhaustive of the entire Stripe API. It includes support for Python and TypeScript, and is built directly on top of the Stripe Python and Node SDKs.

Included below are basic instructions, but refer to Python and TypeScript packages for more information.

Python

Installation

You don't need this source code unless you want to modify the package. If you just want to use the package run:

pip install stripe-agent-toolkit

Requirements

• Python 3.11+

Usage

The library needs to be configured with your account's secret key which is available in your Stripe Dashboard.

from stripe_agent_toolkit.openai.toolkit import StripeAgentToolkit

stripe_agent_toolkit = StripeAgentToolkit(
    secret_key="sk_test_...",
    configuration={
        "actions": {
            "payment_links": {
                "create": True,
            },
        }
    },
)

The toolkit works with OpenAI's Agent SDK, LangChain, and CrewAI and can be passed as a list of tools. For example:

from agents import Agent

stripe_agent = Agent(
    name="Stripe Agent",
    instructions="You are an expert at integrating with Stripe",
    tools=stripe_agent_toolkit.get_tools()
)

Examples for OpenAI's Agent SDK,LangChain, and CrewAI are included in /examples.

Context

In some cases you will want to provide values that serve as defaults when making requests. Currently, the account context value enables you to make API calls for your connected accounts.

stripe_agent_toolkit = StripeAgentToolkit(
    secret_key="sk_test_...",
    configuration={
        "context": {
            "account": "acct_123"
        }
    }
)

TypeScript

Installation

You don't need this source code unless you want to modify the package. If you just want to use the package run:

npm install @stripe/agent-toolkit

Requirements

• Node 18+

Usage

The library needs to be configured with your account's secret key which is available in your Stripe Dashboard. Additionally, configuration enables you to specify the types of actions that can be taken using the toolkit.

import { StripeAgentToolkit } from "@stripe/agent-toolkit/langchain";

const stripeAgentToolkit = new StripeAgentToolkit({
  secretKey: process.env.STRIPE_SECRET_KEY!,
  configuration: {
    actions: {
      paymentLinks: {
        create: true,
      },
    },
  },
});

Tools

The toolkit works with LangChain and Vercel's AI SDK and can be passed as a list of tools. For example:

import { AgentExecutor, createStructuredChatAgent } from "langchain/agents";

const tools = stripeAgentToolkit.getTools();

const agent = await createStructuredChatAgent({
  llm,
  tools,
  prompt,
});

const agentExecutor = new AgentExecutor({
  agent,
  tools,
});

Context

In some cases you will want to provide values that serve as defaults when making requests. Currently, the account context value enables you to make API calls for your connected accounts.

const stripeAgentToolkit = new StripeAgentToolkit({
  secretKey: process.env.STRIPE_SECRET_KEY!,
  configuration: {
    context: {
      account: "acct_123",
    },
  },
});

Supported API methods

See the Stripe MCP docs for a list of supported methods.

License

MIT