convez.ai
MCP ServerIntegração & APIsIntermediário
stripe

Stripe MCP Server

stripe/ai

Integre APIs Stripe com agentes de IA via Model Context Protocol

Ver no GitHub
Muito bomPluginScore · de 0 a 100

Servidor MCP (Model Context Protocol) da Stripe que expõe APIs de pagamentos e billing para agentes de IA. Oferece integração segura via OAuth com ferramentas para gerenciar transações, clientes e assinaturas através de chamadas de função em frameworks de agentes populares.

Instalação

$npx convez-ai stripe/ai

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2,1 mil
Forks
385
Acompanhando
24
Saúde
75%
Último commit
há 1 dia
Versão
—
Issues abertas
47
Contribuidores
38

Casos de uso

  • Automatizar operações de pagamento em agentes de IA
  • Consultar dados de clientes e transações via LLM
  • Construir assistentes de billing e gestão de subscrições
  • Integrar Stripe em workflows com OpenAI, LangChain ou CrewAI

Veredito

Ferramenta essencial para conectar capacidades financeiras da Stripe a agentes de IA. Bem estruturada com suporte multiplataforma (Python/TypeScript) e controle granular de permissões via Restricted API Keys, ideal para produtos que exigem automatização de pagamentos segura.

README

A tradução para o português deste README ainda está na fila.

Hero GIF

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 --api-key=YOUR_STRIPE_SECRET_KEY

Tool permissions are controlled by your Restricted API Key (RAK). Create a RAK with the desired permissions at https://dashboard.stripe.com/apikeys

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. We strongly recommend using a Restricted API Key (rk_*) for better security and granular permissions. Tool availability is determined by the permissions you configure on the restricted key.

from stripe_agent_toolkit.openai.toolkit import create_stripe_agent_toolkit

async def main():
    toolkit = await create_stripe_agent_toolkit(secret_key="rk_test_...")
    tools = toolkit.get_tools()
    # ... use tools ...
    await toolkit.close()  # Clean up when done

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

async def main():
    toolkit = await create_stripe_agent_toolkit(secret_key="rk_test_...")

    stripe_agent = Agent(
        name="Stripe Agent",
        instructions="You are an expert at integrating with Stripe",
        tools=toolkit.get_tools()
    )
    # ... use agent ...
    await toolkit.close()

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.

toolkit = await create_stripe_agent_toolkit(
    secret_key="rk_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+
Migrating from v0.8.x

If you're upgrading from v0.8.x, see the Migration Guide for breaking changes.

Usage

The library needs to be configured with your account's secret key which is available in your Stripe Dashboard. We strongly recommend using a Restricted API Key (rk_*) for better security and granular permissions. Tool availability is determined by the permissions you configure on the restricted key.

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

const toolkit = await createStripeAgentToolkit({
  secretKey: process.env.STRIPE_SECRET_KEY!,
  configuration: {},
});

const tools = toolkit.getTools();
// ... use tools ...

await toolkit.close(); // Clean up when done
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";
import { createStripeAgentToolkit } from "@stripe/agent-toolkit/langchain";

const toolkit = await createStripeAgentToolkit({
  secretKey: process.env.STRIPE_SECRET_KEY!,
  configuration: {},
});

const tools = toolkit.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 toolkit = await createStripeAgentToolkit({
  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

Ver o original no GitHub

Bom para

Relacionados