How to integrate Proabono MCP with Vercel AI SDK v6

GET STARTED FOR FREE
Framework Integration Gradient
Proabono Logo
Vercel AI SDK Logo
divider

Introduction

This guide walks you through connecting Proabono to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Proabono agent that can list all active subscriptions for a customer, create a new subscription for acme corp, show overdue invoices for a specific customer through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Proabono account through Composio's Proabono 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 Proabono integration
  • Using Composio's Tool Router to dynamically load and access Proabono 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 Proabono MCP server, and what's possible with it?

The Proabono MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Proabono account. It provides structured and secure access so your agent can perform Proabono operations on your behalf.

Supported Tools & Triggers

Tools
Anonymize CustomerTool to anonymize a customer for GDPR compliance.
Bill CustomerTool to trigger billing for a customer.
Create CustomerTool to create or declare a customer in ProAbono via the Backoffice API.
Create FeatureTool to create a new feature in ProAbono via the Backoffice API.
Delete CustomerTool to delete a customer from ProAbono by ID.
Delete OfferTool to delete an offer from ProAbono by ID.
Delete Pricing TableTool to delete a pricing table from ProAbono by its ID.
Delete Pricing Table OfferTool to delete a pricing table offer via the ProAbono Backoffice API.
Delete Subscription DiscountTool to delete a subscription discount via the Backoffice API.
Enable WebhookTool to enable a webhook in ProAbono via the Notification API.
Get Customer by IDTool to retrieve a single customer by ID from ProAbono Backoffice API.
Get Customer Billing AddressTool to retrieve a customer's billing address via the Backoffice API.
Get Customer Billing Address by ReferenceTool to retrieve the billing address for a customer by reference from ProAbono API.
Get Customer by ReferenceTool to retrieve a customer by their reference identifier from ProAbono API.
Get Customer Payment SettingsTool to retrieve customer payment settings via the Backoffice API.
Get DiscountTool to retrieve a discount by ID via the Backoffice API.
Get Feature by IDTool to retrieve a feature by ID from ProAbono Backoffice API.
Get Feature by ReferenceTool to retrieve a single feature by its reference from ProAbono API.
Get InvoiceTool to retrieve a specific invoice or credit note by ID from ProAbono.
Get Offer by IDTool to retrieve a single offer by its ID from ProAbono Backoffice API.
Get Subscription by Customer ReferenceTool to retrieve a subscription by customer reference from ProAbono.
Get Subscription Creation QuoteTool to get a pricing quote for creating a new subscription without actually creating it.
Get Usage RecordTool to retrieve a single usage record for a specific feature and customer combination from ProAbono.
Get Usages for CustomerTool to retrieve usage data for customers from ProAbono.
Invalidate CustomerTool to invalidate a customer by their reference.
Invalidate Customer by IDTool to invalidate a customer by their ProAbono internal ID.
List Balance LinesTool to list all balance lines from ProAbono.
List BusinessesTool to list all businesses from ProAbono via the Backoffice API.
List Business LocalizationTool to list localization entries by business from ProAbono via the HostedPages API.
List Customer MovesTool to list all customer balance moves via the ProAbono Backoffice API.
List CustomersTool to list all customers from ProAbono via the Backoffice API.
List Customers by FeatureTool to list customers that have access to a specific feature via the ProAbono API.
List DiscountsTool to list all discounts from ProAbono's Backoffice API.
List FeaturesTool to list all features via the ProAbono Backoffice API.
List Features (V1)Tool to retrieve all features from ProAbono API using the /v1/Features endpoint.
List Gateway AccountsTool to list payment gateway accounts from ProAbono Backoffice API.
List Gateway PermissionsTool to list gateway permissions from ProAbono API.
List Gateway RequestsTool to list gateway requests from ProAbono.
List Gateway TransactionsTool to list gateway transactions from ProAbono.
List Invoice LinesTool to list all invoice lines from ProAbono via the Backoffice API.
List Invoices and Credit NotesTool to list all invoices and credit notes from ProAbono Backoffice API.
List Invoices by Customer ReferenceTool to list invoices for a specific customer by their reference identifier from ProAbono API.
List OffersTool to list all subscription offers (plans) from ProAbono Backoffice API.
List PaymentsTool to list all payments from ProAbono Backoffice API.
List Pricing Table OffersTool to list all pricing table offers via the ProAbono Backoffice API.
List Pricing TablesTool to list all pricing tables from ProAbono Backoffice API.
List Segment LocalizationsTool to list localization entries by segment from ProAbono Backoffice API.
List SegmentsTool to list all segments from ProAbono via the Backoffice API.
List Subscription DiscountsTool to list all subscription discounts via the ProAbono Backoffice API.
List Subscription FeaturesTool to list all subscription features via the ProAbono Backoffice API.
List Subscription PeriodsTool to list all subscription periods (billing cycles) from ProAbono Backoffice API.
List SubscriptionsTool to list all subscriptions from ProAbono via the Backoffice API.
List Subscriptions (V1)Tool to retrieve all subscriptions from ProAbono API using the /v1/Subscriptions endpoint.
List Tax Profile ExceptionsTool to list tax profile exceptions from ProAbono Organization API.
List Tax ProfilesTool to list all tax profiles from ProAbono via the Backoffice API.
List Upgrade OffersTool to retrieve offers available to upgrade an existing customer subscription.
List Webhook NotificationsTool to list webhook notifications from ProAbono via the Notification API.
List WebhooksTool to list webhooks from ProAbono Notification API.
Quote Balance Line CreationTool to get a pricing quote for creating a balance line (one-time charge or credit).
Revoke Customer Portal LinksTool to revoke encrypted customer portal links and generate new ones in ProAbono.
Update Business Billing AddressTool to update business billing address via the Backoffice API.
Update CustomerTool to update an existing customer in ProAbono via the Backoffice API.
Update Customer Billing AddressTool to update the billing address for a customer in ProAbono via the API.
Update Customer Payment SettingsTool to update payment settings for a specific customer in ProAbono.
Update Customer Shipping AddressTool to update customer shipping address via the Backoffice API.
Update FeatureTool to update an existing feature in ProAbono via the Backoffice API.
Update Tax ProfilesTool to update an existing tax profile in ProAbono via the Backoffice API.

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 { 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: ["proabono"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Proabono 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 Proabono-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 Proabono 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 proabono, 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("\nđź‘‹ 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 Proabono 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 Proabono 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: ["proabono"],
  });

  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 proabono, 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("\nđź‘‹ Session ended.");
    process.exit(0);
  });
}

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

Conclusion

You've successfully built a Proabono 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 Proabono MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Proabono MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Proabono MCP with Claude Agent SDK

Google ADK

Google ADK

Use Proabono MCP with Google ADK

LangChain

LangChain

Use Proabono MCP with LangChain

Mastra AI

Mastra AI

Use Proabono MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Proabono MCP with LlamaIndex

CrewAI

CrewAI

Use Proabono MCP with CrewAI

Claude Code

Claude Code

Use Proabono MCP with Claude Code

Codex

Codex

Use Proabono MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Proabono 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 Proabono 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.

Book a call↗Get started for free