How to integrate Quaderno MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Quaderno logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Quaderno to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Quaderno agent that can calculate tax rate for a u.s. sale, create an invoice for a new customer, email finalized invoice to a client through natural language commands.

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

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

Also integrate Quaderno with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Quaderno integration
  • Using Composio's Tool Router to dynamically load and access Quaderno 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 Quaderno MCP server, and what's possible with it?

The Quaderno MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Quaderno account. It provides structured and secure access to your tax automation, invoicing, and compliance workflows, so your agent can calculate taxes, generate invoices, manage contacts and products, and handle essential document delivery on your behalf.

  • Automated tax rate calculation: Ask your agent to instantly determine the correct tax rate for any address or transaction type before creating invoices or processing sales.
  • Invoice creation and delivery: Let your agent generate detailed invoices for customers and deliver them directly via email, ensuring seamless billing operations.
  • Contact and product management: Easily create new customer or vendor contacts, add new products, or permanently delete outdated items from your Quaderno account—all through your agent.
  • Expense and tax ID cleanup: Direct your agent to remove specific expenses or registered tax IDs when they're no longer needed, keeping your records tidy and up to date.
  • Credit note and coupon handling: Your agent can deliver finalized credit notes to customers and permanently delete coupons as part of your accounting and revenue operations.

Supported Tools & Triggers

Tools
Add Expense PaymentAdds a payment to an existing expense in Quaderno.
Calculate Tax RateTool to calculate applicable tax rate for given address and transaction type.
Create ContactTool to create a new contact (customer or vendor).
Create CouponTool to create a new discount coupon in Quaderno.
Create EstimateCreates a new estimate/quote in Quaderno for a customer with line items.
Create EvidenceTool to create a new location evidence for tax compliance.
Create ExpenseTool to create a business expense in Quaderno.
Create InvoiceCreates a new invoice in Quaderno for a customer with line items.
Create ProductCreates a new product that can be used as a line item in invoices, credit notes, and expenses.
Create ReceiptCreates a new receipt in Quaderno documenting payment for goods or services.
Create RecurringTool to create a recurring document in Quaderno that automatically generates invoices on a schedule.
Create Report RequestTool to request a new report generation in Quaderno.
Create Tax IDTool to create a tax ID in a specific jurisdiction.
Create TransactionTool to create a sale or refund transaction in Quaderno.
Create WebhookTool to create a new webhook in Quaderno to receive event notifications.
Delete ContactTool to permanently delete a contact by ID.
Delete CouponTool to permanently delete a coupon.
Delete EstimatePermanently deletes an estimate from Quaderno by its ID.
Delete ExpensePermanently deletes an expense from Quaderno by its ID.
Delete ProductTool to permanently delete a product by ID.
Delete RecurringTool to permanently delete a recurring by ID.
Delete Tax IDPermanently deletes a registered tax ID from your Quaderno account.
Delete WebhookTool to permanently delete a webhook by ID.
Deliver Credit NoteSends a credit note to the customer via email.
Deliver EstimateDelivers an estimate to the customer via email.
Deliver InvoiceDelivers an invoice to the customer via email.
Deliver ReceiptSends a receipt to the customer via email.
Get AuthorizationTool to retrieve account credentials and verify API access.
Get EstimateTool to retrieve the details of an existing estimate by ID.
List ContactsTool to list contacts, paginated and filterable by name, email, or tax ID.
List CouponsTool to list all coupons.
List CreditsTool to list all credit notes from Quaderno.
List EstimatesTool to list all estimates in the account, paginated and sorted by creation date (newest first).
List EvidenceTool to list all evidence objects.
List ExpensesList all expenses from Quaderno with pagination support.
List InvoicesTool to list all invoices from Quaderno with filtering support.
List Tax JurisdictionsTool to list all tax jurisdictions.
List ProductsList all products (goods and services) from your Quaderno account.
List ReceiptsTool to list all receipts from Quaderno with optional filtering by search query, date range, payment state, processor ID, or customer ID.
List RecurringsList all recurring documents (invoices, expenses, or estimates) from your Quaderno account.
List Registered Tax IDsTool to list all registered tax IDs.
List Reporting RequestsRetrieves all reporting requests for the account with their current status and download URLs.
List SessionsList Quaderno Checkout sessions with optional filtering and pagination.
List Tax CodesTool to list all supported tax codes.
List WebhooksTool to list all webhooks.
Mark Invoice UncollectibleTool to mark an invoice as uncollectible (bad debt).
Ping API ServiceTool to check if the Quaderno API service is up and verify credentials.
Record Invoice PaymentTool to record a payment on an existing invoice.
Remove Invoice PaymentTool to remove a payment from an invoice.
Retrieve ContactTool to retrieve details of an existing contact by ID.
Retrieve Contact by Processor IDTool to retrieve a contact by external payment processor customer ID and gateway name.
Retrieve CouponRetrieve detailed information about a specific coupon by its ID.
Retrieve Credit NoteTool to retrieve details of an existing credit note by ID.
Retrieve EvidenceRetrieves a specific evidence object by its ID.
Retrieve ExpenseTool to retrieve details of an existing expense by ID.
Retrieve InvoiceTool to retrieve details of an existing invoice by ID.
Retrieve Tax JurisdictionTool to retrieve a tax jurisdiction by ID.
Retrieve ProductTool to retrieve details of an existing product by ID.
Retrieve ReceiptTool to retrieve details of an existing receipt by ID.
Retrieve RecurringTool to retrieve details of an existing recurring document by ID.
Retrieve Reporting RequestTool to retrieve the status and download URL of a specific report request by ID.
Retrieve Tax CodeTool to retrieve a specific tax code by ID.
Retrieve Tax IDTool to retrieve details of a specific tax ID by its ID.
Update ContactTool to update an existing contact in Quaderno.
Update CouponTool to update an existing coupon.
Update Credit NoteTool to update a credit note.
Update EstimateUpdates an existing estimate in Quaderno by modifying allowed fields.
Update EvidenceTool to update an evidence object.
Update ExpenseUpdates an existing expense in Quaderno by modifying allowed fields.
Update InvoiceUpdates an existing invoice in Quaderno by modifying allowed fields.
Update productTool to update a product; unspecified fields remain unchanged.
Update RecurringTool to update a recurring document in Quaderno.
Update Tax IDTool to update an existing tax ID in Quaderno.
Update WebhookTool to update an existing webhook configuration.
Validate Tax IDTool to validate a tax ID.
Void Credit NoteTool to void a credit note.

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: ["quaderno"],
  });

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

  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 quaderno, 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 Quaderno 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 Quaderno MCP Agent with another framework

FAQ

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

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

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

Yes, absolutely. You can configure which Quaderno 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 Quaderno 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.