How to integrate Stripe MCP with Vercel AI SDK

Framework Integration Gradient
Stripe Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Stripe to Vercel AI SDK using the Composio tool router. By the end, you'll have a working Stripe agent that can create a new stripe customer with email, generate a draft invoice for recent orders, cancel an active subscription at period end, issue a refund for a specific payment through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Stripe account through Composio's Stripe MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Stripe integration
  • Using Composio's Tool Router to dynamically load and access Stripe tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol
  • Step Counting: Control multi-step tool execution
  • OpenAI Provider: Native integration with OpenAI models

What is the Stripe MCP server, and what's possible with it?

The Stripe MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Stripe account. It provides structured and secure access to your payments platform, so your agent can perform actions like creating customers, managing subscriptions, issuing refunds, and generating invoices on your behalf.

  • Automated customer management: Effortlessly create, update, or delete Stripe customers—enabling streamlined onboarding and account maintenance through your agent.
  • Subscription and recurring billing automation: Have your agent create, configure, or cancel subscriptions, supporting trials, discounts, and advanced billing scenarios with ease.
  • Smart payment and refund processing: Allow your agent to initiate payment intents, confirm transactions, and issue full or partial refunds as needed, all through secure APIs.
  • Seamless invoice and price creation: Generate draft invoices for customers, create new products, and set up pricing structures—saving you time on manual billing tasks.
  • Advanced product and pricing management: Let your agent create new products and prices, helping you roll out new offerings or adjust monetization strategies with just a prompt.

Supported Tools & Triggers

Tools
Triggers
Cancel subscriptionCancels a customer's active stripe subscription at the end of the current billing period, with options to invoice immediately for metered usage and prorate charges for unused time.
Confirm payment intentConfirms a stripe paymentintent to finalize a payment; a `return url` is necessary if the payment method requires customer redirection.
Create CustomerCreates a new customer in stripe, required for creating charges or subscriptions; an email is highly recommended for customer communications.
Create an invoiceCreates a new draft stripe invoice for a customer; use to revise an existing invoice, bill for a specific subscription (which must belong to the customer), or apply detailed customizations.
Create payment intentCreates a stripe paymentintent to initiate and process a customer's payment; using `application fee amount` for a connected account requires the `stripe-account` header.
Create a priceCreates a new stripe price for a product, defining its charges (one-time or recurring) and billing scheme; requires either an existing `product` id or `product data`.
Create productCreates a new product in stripe, encoding the request as `application/x-www-form-urlencoded` by flattening nested structures.
Create RefundCreates a full or partial refund in stripe, targeting either a specific charge id or a payment intent id.
Create subscriptionCreates a new, highly configurable subscription for an existing stripe customer, supporting multiple items, trials, discounts, and various billing/payment options.
Delete customerPermanently deletes an existing stripe customer; this irreversible action also cancels their active subscriptions and removes all associated data.
List ChargesRetrieves a list of stripe charges with filtering and pagination; use valid cursor ids from previous responses for pagination, and note that charges are typically returned in reverse chronological order.
List Stripe couponsRetrieves a list of discount coupons from a stripe account, supporting pagination via `limit`, `starting after`, and `ending before`.
List customer payment methodsRetrieves a list of payment methods for a given customer, supporting type filtering and pagination.
List customersRetrieves a list of stripe customers, with options to filter by email, creation date, or test clock, and support for pagination.
List InvoicesRetrieves a list of stripe invoices, filterable by various criteria and paginatable using invoice id cursors obtained from previous responses.
List payment intentsRetrieves a list of stripe paymentintents, optionally filtered and paginated using paymentintent ids as cursors.
List payment linksRetrieves a list of payment links from stripe, sorted by creation date in descending order by default.
List productsRetrieves a list of stripe products, with optional filtering and pagination; `starting after`/`ending before` cursors must be valid product ids from a previous response.
List RefundsLists stripe refunds, sorted by creation date descending (newest first), with optional filtering by charge or payment intent and pagination support.
List Stripe shipping ratesRetrieves a list of stripe shipping rates, filterable by active status, creation date, and currency; useful for managing or displaying shipping options.
List subscriptionsRetrieves a list of stripe subscriptions, optionally filtered by various criteria such as customer, price, status, collection method, and date ranges, with support for pagination.
List tax codesRetrieves a paginated list of globally available, predefined stripe tax codes used for classifying products and services in stripe tax.
List tax ratesRetrieves a list of tax rates, which are returned sorted by creation date in descending order.
Retrieve BalanceRetrieves the complete current balance details for the connected stripe account.
Retrieve Charge DetailsRetrieves full details for an existing stripe charge using its unique id.
Retrieve customerRetrieves detailed information for an existing stripe customer using their unique customer id.
Retrieve payment intentRetrieves a paymentintent by its id; `client secret` is required if a publishable api key is used.
Retrieve a refundRetrieves details for an existing stripe refund using its unique `refund id`.
Retrieve subscriptionRetrieves detailed information for an existing stripe subscription using its unique id.
Search Stripe customersRetrieves a list of stripe customers matching a search query that adheres to stripe's search query language.
Update CustomerUpdates an existing stripe customer, identified by customer id, with only the provided details; unspecified fields remain unchanged.
Update Payment IntentUpdates a stripe paymentintent with new values for specified parameters; note that if `currency` is updated, `amount` might also be required, and certain updates (e.
Update SubscriptionUpdates an existing, non-canceled stripe subscription by its id, ensuring all referenced entity ids (e.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { experimental_createMCPClient as createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const { session } = await composio.create(composioUserID!, {
    toolkits: ["stripe"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Stripe tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Stripe-related tools through the MCP protocol

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Stripe tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to stripe, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Stripe tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Stripe and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { experimental_createMCPClient as createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const { session } = await composio.create(composioUserID!, {
    toolkits: ["stripe"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to stripe, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Stripe agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Stripe MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Stripe MCP?

With a standalone Stripe MCP server, the agents and LLMs can only access a fixed set of Stripe tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Stripe and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Vercel AI SDK?

Yes, you can. Vercel AI SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Stripe tools.

Can I manage the permissions and scopes for Stripe while using Tool Router?

Yes, absolutely. You can configure which Stripe scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Stripe data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.