How to integrate Altoviz MCP with Vercel AI SDK v6

This guide walks you through connecting Altoviz to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Altoviz agent that can find customer details by email address, update a client's company information, retrieve current vat rates for invoices through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Altoviz account through Composio's Altoviz MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for free Get a demo

Altoviz

Api Key

Altoviz is a cloud-based billing and invoicing platform for businesses. It streamlines online payments, expense tracking, and customizable invoice management.

67 Tools

Managed auth

Connect Altoviz without auth hassles

We manage OAuth, API keys, token refresh, and scopes — you just build.

Try for free

Introduction

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

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

Also integrate Altoviz with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Altoviz integration
Using Composio's Tool Router to dynamically load and access Altoviz 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 Altoviz MCP server, and what's possible with it?

The Altoviz MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Altoviz account. It provides structured and secure access to your billing, invoicing, and customer management data, so your agent can manage products, find customers, update records, and retrieve financial information on your behalf.

Product management and creation: Instruct your agent to create new products, update details, or delete products from your Altoviz catalog with ease.
Customer and contact lookup: Effortlessly find customers or contacts by email, enabling quick access to client details and supporting streamlined communication.
Financial classification and VAT management: Let your agent fetch available classifications and VAT rates, ensuring accurate tax handling and financial document setup.
Unit retrieval for transactions: Retrieve all available measurement units in your system, supporting precise product and invoice management.
Customer information updates: Have your agent modify or update customer records, keeping your business data up-to-date without manual intervention.

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:

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

Step-by-step Guide

Step by step09 STEPS

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: ["altoviz"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Altoviz 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 Altoviz-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 Altoviz 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 altoviz, 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 Altoviz 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 Altoviz 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: ["altoviz"],
  });

  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 altoviz, 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 Altoviz 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.

TOOLS

Supported Tools

Every Altoviz action and event your agent gets out of the box.

Create Contact

Creates a new contact in the Altoviz system.

Create Customer

Creates a new customer in Altoviz.

Create Customer Family

Creates a new customer family in Altoviz for categorizing and organizing customers into groups.

Create Product

Creates a new product in the Altoviz system.

Create Product Family

Tool to create a new product family in Altoviz.

Create Receipt

Creates a new receipt in the Altoviz system to record customer payments.

Create Sale Credit

Creates a new draft credit note (avoir) in Altoviz.

Create Sale Invoice

Creates a new draft sale invoice in Altoviz.

Delete Colleague

Tool to delete a colleague from Altoviz.

Delete Customer

Tool to delete a customer from Altoviz.

Delete Customer Family

Tool to delete a customer family from Altoviz.

Delete Product

This tool allows you to delete an existing product from Altoviz.

Delete Product Family

Tool to delete a product family from Altoviz.

Delete Receipt

Tool to delete a receipt from Altoviz.

Delete Draft Sale Credit

Tool to delete a draft credit from Altoviz.

Delete Sale Invoice

Tool to delete a draft sale invoice from Altoviz.

Delete Sale Quote

Tool to delete a sale quote from Altoviz.

Delete Supplier

Tool to delete a supplier from Altoviz.

Download Purchase Invoice

Tool to download a purchase invoice as a PDF file from Altoviz.

Download Sale Credit PDF

Tool to download a sale credit as a PDF file from Altoviz.

Download Sale Invoice PDF

Tool to download a sale invoice as a PDF file from Altoviz.

Find Contact by Email

This tool allows searching for contacts in Altoviz using an email address.

Find Customer by Email

This tool allows you to find a customer in Altoviz by their email address.

Find Product by Number

Search for a product in Altoviz by its product number/SKU.

Find Product by Number or Internal ID

Tool to find a product in Altoviz by exact product number or internal ID.

Find Receipt by Internal ID

Tool to find receipts in Altoviz by customer internal ID.

Find Sale Credits

Tool to find sale credits in Altoviz.

Find Sale Invoices

Tool to find sale invoices in Altoviz.

Find Sale Quotes

Tool to find sale quotes in Altoviz.

Get Classifications List

This tool retrieves a list of classifications from the Altoviz platform.

Get Colleague by ID

Tool to retrieve a colleague's details from Altoviz by their ID.

Get Contact by ID

Tool to retrieve a contact by its unique ID from Altoviz.

Get Current User

Tool to retrieve the current authenticated user's information from Altoviz.

Get Customer by ID

Tool to retrieve a customer by their ID from Altoviz.

Get Customer by Internal ID

Tool to retrieve a single customer from Altoviz by their internal ID.

Get Customer Contacts

Tool to retrieve all contacts associated with a specific customer in Altoviz.

Get Customer Family

Tool to retrieve a customer family by ID from Altoviz.

Get Product by ID

Tool to retrieve a product by its unique ID in Altoviz.

Get Product Family by ID

Tool to retrieve a specific product family by its ID from Altoviz.

Get Receipt by ID

Tool to retrieve a receipt by its ID from Altoviz.

Get Sale Credit by ID

Tool to retrieve a sale credit by its ID from Altoviz.

Get Sale Invoice by ID

Tool to retrieve a sale invoice by its ID from Altoviz.

Get Settings

Tool to retrieve application settings from Altoviz.

Get Supplier by ID

Tool to retrieve a supplier by their ID from Altoviz.

Get Supplier Contacts

Tool to retrieve all contacts associated with a specific supplier in Altoviz.

Get Units List

This tool retrieves a list of all available units in the Altoviz system.

Get VAT Rates

This tool retrieves a list of all available VAT rates from Altoviz.

List Colleagues

Retrieves a list of colleagues from Altoviz.

List Contacts

Tool to retrieve a list of contacts from Altoviz with optional filtering and pagination.

List Customer Families

Tool to list customer families from Altoviz.

List Customers

Tool to retrieve a paginated list of customers from Altoviz.

List Product Families

Tool to retrieve a list of product families from Altoviz.

List Receipts

Tool to retrieve a list of receipts from Altoviz.

List Sale Credits

Tool to retrieve a list of sale credits from Altoviz.

List Sale Invoices

Tool to retrieve a list of sale invoices from Altoviz.

List Sale Quotes

Tool to retrieve a list of sale quotes from Altoviz.

List Suppliers

Tool to retrieve a paginated list of suppliers from Altoviz.

List Webhooks

Tool to retrieve all configured webhooks from Altoviz.

Tool to register a new webhook in Altoviz.

Test API Key

Tool to test API key validity and retrieve basic account information.

Unregister Webhook

Tool to unregister a webhook from Altoviz.

Update Colleague Information

Updates an existing colleague's information in Altoviz.

Update Customer Information

Updates an existing customer's information in Altoviz.

Update Receipt

Updates an existing receipt in Altoviz.

Update Sale Credit

Tool to update a draft credit note in Altoviz.

Update Supplier Information

Updates an existing supplier's information in Altoviz.

Upload Purchase Invoice

Tool to upload and create a new purchase invoice from a file (PDF or image format).

FRAMEWORKS

How to build Altoviz MCP Agent with another framework

OpenAI Agents SDK

Use Altoviz MCP with OpenAI Agents SDK

Claude Agent SDK

Use Altoviz MCP with Claude Agent SDK

Claude Code

Use Altoviz MCP with Claude Code

Claude Cowork

Use Altoviz MCP with Claude Cowork

Codex

Use Altoviz MCP with Codex

OpenClaw

Use Altoviz MCP with OpenClaw

Hermes

Use Altoviz MCP with Hermes

CLI

Use Altoviz MCP with CLI

Google ADK

Use Altoviz MCP with Google ADK

LangChain

Use Altoviz MCP with LangChain

Mastra AI

Use Altoviz MCP with Mastra AI

LlamaIndex

Use Altoviz MCP with LlamaIndex

CrewAI

Use Altoviz MCP with CrewAI

MORE TOOLKITS

Explore Other Toolkits

Toolkit marketplace

Stripe

Api KeyOauth2

Stripe is a global online payments platform offering APIs for managing payments, customers, and subscriptions. Trusted by businesses for secure, efficient, and scalable payment processing worldwide.

Alpha vantage

Api Key

Alpha Vantage is a financial data platform offering real-time and historical stock market APIs. Get instant, reliable access to equities, forex, and technical analysis data for smarter trading decisions.

Benzinga

Api Key

Benzinga provides real-time financial news and data APIs for market coverage. It helps you track breaking news and actionable market insights instantly.

Brex

Oauth2Api Key

Brex provides corporate credit cards and spend management tailored for startups and tech businesses. It helps optimize company cash flow, streamline accounting, and accelerate business growth.

FAQ

Frequently asked questions

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

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 Altoviz tools.

Yes, absolutely. You can configure which Altoviz 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.

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 Altoviz data and credentials are handled as safely as possible.

Start with Altoviz.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Altoviz tool your agent needs.Free to start.

Start building

Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREE BOOK A DEMO

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati

Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya

Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave

CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu

Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola

Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche

Co-Founder, Ingram Technologies

How to integrate Altoviz MCP with Vercel AI SDK v6

Connect Altoviz without auth hassles

Introduction

Also integrate Altoviz with

TL;DR

What is Vercel AI SDK?

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

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

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

Complete Code

Conclusion

Supported Tools

How to build Altoviz MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Stripe

Alpha vantage

Benzinga

Brex

Frequently asked questions

What are the differences in Tool Router MCP and Altoviz MCP?+

Can I use Tool Router MCP with Vercel AI SDK v6?+

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

How safe is my data with Composio Tool Router?+

Start with Altoviz.It takes 30 seconds.

Teams ship real agents on Composio