Stripe Agent Toolkit
Featuredby
Enables popular agent frameworks to integrate with Stripe APIs via function calling, providing tools for MCP, Python, and TypeScript.
Stripe Agent Toolkit Overview
What is Stripe Agent Toolkit about?
Enables popular agent frameworks—including Model Context Protocol (MCP), OpenAI's Agent SDK, LangChain, CrewAI, and Vercel's AI SDK—to call Stripe APIs through function calling. The library builds on the official Stripe Python and Node SDKs and offers a curated set of API actions.
How to use Stripe Agent Toolkit?
Installation
- Python:
pip install stripe-agent-toolkit(requires Python 3.11+). - TypeScript/Node:
npm install @stripe/agent-toolkit(requires Node 18+).
Configuration
Create an instance of StripeAgentToolkit with your secret key and an optional configuration object to enable specific actions or set context values (e.g., connected account ID).
from stripe_agent_toolkit.openai.toolkit import StripeAgentToolkit
toolkit = StripeAgentToolkit(
secret_key="sk_test_...",
configuration={"actions": {"payment_links": {"create": True}}},
)
import { StripeAgentToolkit } from "@stripe/agent-toolkit/langchain";
const toolkit = new StripeAgentToolkit({
secretKey: process.env.STRIPE_SECRET_KEY!,
configuration: { actions: { paymentLinks: { create: true } } },
});
Pass toolkit.get_tools() to your agent framework (OpenAI Agent SDK, LangChain, CrewAI, Vercel AI SDK, etc.).
Key features of Stripe Agent Toolkit
- MCP tool exposure with optional local server (
npx -y @stripe/mcp). - Python library compatible with OpenAI Agent SDK, LangChain, CrewAI.
- TypeScript library compatible with LangChain and Vercel AI SDK.
- Configurable actions – enable only the Stripe endpoints you need.
- Context support – default
accountvalue for connected‑account requests. - Metered billing middleware for Vercel AI SDK (customer ID + token meters).
- Supported API methods include creating customers, payment links, products, prices, subscriptions, refunds, coupons, invoices, and related list/retrieve/update operations.
Use cases of Stripe Agent Toolkit
- Build AI assistants that can create payment links or manage subscriptions on behalf of users.
- Automate billing workflows in SaaS products using LLM agents.
- Enable conversational checkout experiences in chatbots.
- Provide metered AI usage billing tied to Stripe customers via Vercel AI SDK.
- Rapid prototyping of agentic workflows that require Stripe interactions without writing custom API calls.
FAQ
Q: Do I need to clone the repository to use the toolkit?
A: No. Install the published packages via pip or npm. Clone only if you intend to modify the source.
Q: Can I use the toolkit with frameworks other than the ones listed?
A: Yes. As long as the framework accepts a list of tool definitions compatible with the OpenAI function‑calling schema, you can pass toolkit.get_tools().
Q: How do I run a local MCP server?
A: Run npx -y @stripe/mcp --tools=all --api-key=YOUR_STRIPE_SECRET_KEY.
Q: What Python version is required? A: Python 3.11 or newer.
Q: Is the library exhaustive of the Stripe API? A: No. It currently supports a curated subset of common endpoints (see the "Supported API methods" list).
Stripe Agent Toolkit's README
Stripe Agent Toolkit
The Stripe Agent Toolkit enables popular agent frameworks including Model Context Protocol (MCP), 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 MCP, Python, and TypeScript and is built directly on top of the Stripe Python and Node SDKs.
Included below are basic instructions, but refer to the MCP Python, TypeScript packages for more information.
Model Context Protocol
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
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",
},
},
});
Metered billing
For Vercel's AI SDK, you can use middleware to submit billing events for usage. All that is required is the customer ID and the input/output meters to bill.
import { StripeAgentToolkit } from "@stripe/agent-toolkit/ai-sdk";
import { openai } from "@ai-sdk/openai";
import {
generateText,
experimental_wrapLanguageModel as wrapLanguageModel,
} from "ai";
const stripeAgentToolkit = new StripeAgentToolkit({
secretKey: process.env.STRIPE_SECRET_KEY!,
configuration: {
actions: {
paymentLinks: {
create: true,
},
},
},
});
const model = wrapLanguageModel({
model: openai("gpt-4o"),
middleware: stripeAgentToolkit.middleware({
billing: {
customer: "cus_123",
meters: {
input: "input_tokens",
output: "output_tokens",
},
},
}),
});
Supported API methods
- Cancel a subscription
- Create a coupon
- Create a customer
- Create a payment link
- Create a price
- Create a product
- Create a refund
- Create an invoice item
- Create an invoice
- Finalize an invoice
- List all coupons
- List all customers
- List all disputes
- List all prices
- List all products
- List all subscriptions
- Retrieve balance
- Update a dispute
- Update a subscription
Stripe Agent Toolkit Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Stripe Agent Toolkit's Information
- Author
- stripe
- Category
- Finance & Payments
- Language
- TypeScript
- License
- MIT License
- Stars
- 965
- Updated
- 19 days ago
Configuration
{
"mcpServers": {
"stripe-mcp": {
"command": "npx",
"args": [
"-y",
"@stripe/mcp",
"--tools=all",
"--api-key=YOUR_STRIPE_SECRET_KEY"
],
"env": {
"API_KEY": "<YOUR_API_KEY>"
}
}
}
}Configure Clients
Related MCP Servers
Discover more MCP servers with similar functionality and use cases
GOAT
by goat-sdk
GOAT is the largest agentic finance toolkit for AI agents, enabling them to become economic actors by leveraging blockchains, cryptocurrencies, and wallets.
Financial Datasets MCP Server
by financial-datasets
Provides AI assistants with tools to retrieve income statements, balance sheets, cash flow statements, stock prices, market news, and crypto information via the Model Context Protocol.
Razorpay MCP Server
by razorpay
Enables seamless interaction with Razorpay APIs via Model Context Protocol, allowing developers and AI agents to capture payments, manage orders, process refunds, handle settlements, and more through a unified MCP interface.
Armor Crypto MCP
Officialby armorwallet
Armor Crypto MCP provides a unified interface for AI agents to interact with the crypto ecosystem, including wallet management, swaps, staking, and multi-chain operations.
Alpaca
Officialby alpacahq
Alpaca’s MCP server lets you trade stocks and options, analyze market data, and build strategies through Alpaca's Trading API.
Xero MCP Server
by XeroAPI
Provides a bridge between the Model Context Protocol and Xero's API, enabling standardized access to Xero accounting and business features.
Freqtrade MCP
by kukapay
Integrates the Freqtrade cryptocurrency trading bot with an MCP server, exposing the bot's REST API as tools that AI agents can call for fully automated trading operations.
Crypto Indicators
by kukapay
Offers over 50 cryptocurrency technical analysis indicators and corresponding trading strategies, enabling AI agents and developers to assess market trends and generate buy, hold, or sell signals.
SEC EDGAR
by stefanoamorelli
SEC EDGAR MCP is an open-source MCP server that connects AI models to the rich dataset of SEC EDGAR filings. It makes the trove of public company data accessible to AI assistants (LLMs) for financial research, investment insights, and corporate transparency use cases.