How to integrate Square MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Square logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Square to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Square agent that can create and send an invoice to a customer, list all recent payments from last week, update item prices in your product catalog through natural language commands.

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

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

Also integrate Square with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Square integration
  • Using Composio's Tool Router to dynamically load and access Square 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 via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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

The Square MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Square account. It provides structured and secure access to your Square business tools, so your agent can perform actions like processing payments, managing invoices, tracking orders, handling customers, and managing inventory on your behalf.

  • Seamless payment processing: Let your agent accept card payments, issue refunds, and manage transactions across your business locations.
  • Automated invoice creation and management: Ask your agent to generate, send, and monitor invoices for your customers, streamlining your billing process.
  • Order and fulfillment tracking: Enable your agent to view, update, and manage orders, helping you keep tabs on fulfillment and delivery status with ease.
  • Customer profile management: Have your agent create, update, or search customer profiles, making it easier to personalize service and maintain up-to-date records.
  • Inventory and item catalog control: Allow your agent to track stock levels, update item details, and organize your catalog for smooth retail operations.

Supported Tools & Triggers

Tools
Accept DisputeAccept a dispute and acknowledge liability, returning funds to the cardholder.
Add Group to CustomerTool to add a customer to a customer group.
Calculate OrderTool to preview order pricing without creating an order.
Cancel InvoiceCancels a Square invoice, preventing further payments from being collected.
Cancel PaymentCancels (voids) a payment that is in APPROVED status.
Create Bulk CustomersTool to create multiple customer profiles in a single request.
Create CardTool to create a card on file.
Create CustomerTool to create a new customer profile in Square.
Create Customer Custom Attribute DefinitionTool to create a customer-related custom attribute definition.
Create Customer GroupTool to create a new customer group for a business.
Create Dispute Evidence FileTool to upload a file as dispute evidence.
Create Dispute Evidence TextUpload text evidence for a dispute challenge.
Create Invoice AttachmentUpload and attach a file to a Square invoice.
Create LocationTool to create a new business location in a Square account.
Create Location Custom Attribute DefinitionTool to create a location-related custom attribute definition.
Delete CustomerTool to delete a Square customer profile.
Delete Customer Custom AttributeTool to delete a custom attribute from a customer profile.
Delete Customer Custom Attribute DefinitionTool to delete a customer-related custom attribute definition.
Delete Customer GroupTool to delete a customer group by its ID.
Bulk Delete CustomersTool to bulk delete customer profiles from Square.
Delete Dispute EvidenceRemoves a specific piece of evidence from a dispute.
Delete InvoiceTool to delete a Square invoice (only DRAFT invoices can be deleted).
Delete Invoice AttachmentTool to delete an attachment from a Square invoice.
Delete Location Custom AttributeTool to delete a custom attribute from a location.
Delete Location Custom Attribute DefinitionTool to delete a location-related custom attribute definition.
Delete Locations Custom Attributes (Batch)Tool to delete custom attributes from multiple locations in a single batch request.
Delete Merchant Custom AttributeTool to delete a custom attribute from a merchant profile.
Delete Merchant Custom Attribute DefinitionTool to delete a merchant-related custom attribute definition.
Delete Merchants Custom Attributes (Batch)Tool to delete custom attributes from multiple merchants in a single batch request.
Delete Webhook SubscriptionPermanently deletes a webhook subscription by its ID.
Get Business Booking ProfileTool to retrieve the business booking profile for a Square merchant via GraphQL.
Get Current MerchantTool to retrieve merchant information associated with the access token using Square's GraphQL API.
Get Customer Custom AttributeRetrieves a custom attribute from a customer profile in Square.
Get Customer Custom Attribute DefinitionTool to retrieve a customer-related custom attribute definition from Square.
Get Customers via GraphQLTool to retrieve customer profiles from Square Customer Directory using GraphQL API.
Get Dispute EvidenceRetrieves detailed information about a specific piece of evidence that was uploaded for a dispute.
Get InvoiceRetrieves detailed information about a specific Square invoice by its ID.
Get MerchantTool to retrieve detailed information about a specific Square merchant by ID.
Get Online Checkout Location SettingsTool to retrieve location-level settings for Square online checkout.
List ChannelsTool to list requested channels from Square.
List Customer Custom Attribute DefinitionsTool to list customer-related custom attribute definitions from Square.
List Customer Custom Attribute Definitions (GraphQL)Tool to retrieve customer custom attribute definitions via Square's GraphQL API.
List Customer Custom AttributesTool to list custom attributes for a customer profile.
List Customer GroupsTool to retrieve the list of customer groups of a business.
List CustomersTool to retrieve customer profiles associated with a Square account.
List Customer SegmentsTool to retrieve the list of customer segments of a business.
List Dispute EvidenceTool to list evidence items associated with a given dispute.
List InvoicesTool to list invoices for a Square location.
List Location Custom Attribute DefinitionsTool to list location-related custom attribute definitions from Square.
List LocationsTool to retrieve all business locations from a Square account.
List Locations Custom AttributesTool to list custom attributes for a specific location in Square.
List Merchant Custom Attribute DefinitionsTool to list merchant-related custom attribute definitions from Square.
List MerchantsTool to retrieve merchant account information associated with the access token.
List Merchants Custom AttributesTool to list custom attributes for a specific merchant in Square.
List PaymentsTool to list payments by location and time range to enable reconciliation and net sales reporting from Square POS.
List Webhook Event TypesTool to list available webhook event types.
List Webhook SubscriptionsList all webhook subscriptions owned by your application.
Remove Group From CustomerRemoves a customer from a customer group.
Retrieve Bulk CustomersTool to retrieve multiple customer profiles in a single request.
Retrieve ChannelRetrieve a Square channel by its ID.
Bulk Retrieve ChannelsTool to bulk retrieve multiple Square channels by their IDs in a single request.
Retrieve CustomerTool to retrieve detailed information about a specific Square customer by ID.
Retrieve Customer GroupTool to retrieve a specific Square customer group by ID.
Retrieve Customer SegmentTool to retrieve a specific customer segment by its ID.
Retrieve DisputeTool to retrieve a Square dispute by ID.
Retrieve LocationTool to retrieve detailed information about a specific Square location by ID.
Retrieve Location Custom AttributeRetrieves a custom attribute associated with a location in Square.
Retrieve Location Custom Attribute DefinitionTool to retrieve a location-related custom attribute definition.
Retrieve Merchant Custom AttributeRetrieves a custom attribute associated with a merchant in Square.
Retrieve Merchant Custom Attribute DefinitionTool to retrieve a merchant-related custom attribute definition from Square.
Retrieve MerchantsTool to retrieve merchant information including status, main location details, and capabilities using Square's GraphQL API.
Retrieve OrderRetrieves detailed information about a specific Square order by its ID.
Retrieve Payment LinkRetrieves a Square-hosted payment link by ID.
Retrieve Token StatusTool to retrieve information about an OAuth access token or personal access token.
Retrieve Webhook SubscriptionRetrieve a Square webhook subscription by its ID.
Search CustomersTool to search customer profiles in Square Customer Directory.
Search OrdersTool to search orders across one or more Square locations with filters.
Submit Dispute EvidenceSubmits evidence for a dispute to the cardholder's bank.
Test Webhook SubscriptionTests a webhook subscription by sending a test event to the configured notification URL.
Update CustomerTool to update an existing Square customer profile.
Update Customer Custom Attribute DefinitionTool to update a customer-related custom attribute definition in Square.
Update Customer GroupTool to update a customer group's information by its ID.
Bulk Update CustomersTool to update multiple customer profiles in a single batch operation.
Update LocationTool to update an existing business location in a Square account.
Update Location Custom Attribute DefinitionTool to update a location-related custom attribute definition in Square.
Update Merchant Custom Attribute DefinitionTool to update a merchant-related custom attribute definition in Square.
Update Online Checkout Location SettingsTool to update location-level settings for Square online checkout.
Update OrderUpdates an existing Square order by adding, modifying, or removing fields.
Update Webhook SubscriptionTool to update a Square webhook subscription.
Update Webhook Subscription Signature KeyTool to rotate the signature key for a webhook subscription.
Upsert Customer Custom AttributeTool to create or update a custom attribute for a customer profile.
Batch Upsert Customer Custom AttributesTool to create or update custom attributes for multiple customers in a single batch request.
Upsert Location Custom AttributeTool to create or update a custom attribute for a location.
Batch Upsert Locations Custom AttributesTool to create or update custom attributes for multiple locations in a single batch request.
Upsert Merchant Custom AttributeTool to create or update a custom attribute for a merchant profile.
Batch Upsert Merchants Custom AttributesTool to create or update custom attributes for multiple merchants in a single batch request.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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 { 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: ["square"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Square 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 Square-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 Square 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 square, 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 Square 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 Square 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 { 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: ["square"],
  });

  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 square, 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 Square 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 Square MCP Agent with another framework

FAQ

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

With a standalone Square MCP server, the agents and LLMs can only access a fixed set of Square tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Square 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 v6?

Yes, you can. Vercel AI SDK v6 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 Square tools.

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

Yes, absolutely. You can configure which Square 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 Square data and credentials are handled as safely as possible.

Used by agents from

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