How to integrate Lexoffice MCP with Vercel AI SDK v6

This guide walks you through connecting Lexoffice to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Lexoffice agent that can generate and send new client invoices, summarize monthly expense reports, list overdue payments from customers through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Lexoffice account through Composio's Lexoffice MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Lexoffice logoLexoffice
Api Key

Lexoffice is a cloud-based accounting platform for freelancers and small businesses. It streamlines invoicing, expense tracking, and integrates directly with your bank for hassle-free bookkeeping.

41 Tools

Introduction

This guide walks you through connecting Lexoffice to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Lexoffice agent that can generate and send new client invoices, summarize monthly expense reports, list overdue payments from customers through natural language commands.

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

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

Also integrate Lexoffice with

TL;DR

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

The Lexoffice MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Lexoffice account. It provides structured and secure access to your Lexoffice workspace, so your agent can perform actions like managing invoices, tracking expenses, syncing with bank accounts, and handling client records on your behalf.

  • Invoice creation and management: Effortlessly generate, send, and track invoices, helping you streamline your billing process.
  • Expense tracking and categorization: Let your agent log and classify expenses, making it easy to stay on top of your business spending.
  • Bank integration and reconciliation: Automatically sync transactions with your connected bank accounts for simplified reconciliation and financial oversight.
  • Client and contact management: Manage your customer database, update records, and keep client information organized and up to date.
  • Financial reporting and insights: Generate detailed reports on your business’s financial health, including revenue, expenses, and outstanding balances.

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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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
6

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: ["lexoffice"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Lexoffice 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 Lexoffice-related tools through the MCP protocol
7

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 Lexoffice tools that the agent can use
8

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 lexoffice, 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
9

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 Lexoffice 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 Lexoffice 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: ["lexoffice"],
  });

  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 lexoffice, 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 Lexoffice 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 Lexoffice action and event your agent gets out of the box.

Create Article

Tool to create a new article (product or service) in Lexoffice.

Create contact

Tool to create a new contact (customer or vendor) in Lexoffice.

Create Credit Note

Tool to create a credit note in Lexoffice.

Create Delivery Note

Create a delivery note in lexoffice.

Create Event Subscription

Tool to register a new webhook for Lexoffice events.

Create Order Confirmation

Tool to create an Order Confirmation in Lexoffice/Lexware.

Create Quotation

Tool to create a quotation in Lexoffice.

Create Voucher

Tool to create a bookkeeping voucher in Lexoffice.

Delete Article

Tool to permanently delete an article by its ID.

Delete Event Subscription

Tool to delete an event subscription by its ID.

Download File

Download a file from lexoffice by its ID.

Get Article

Tool to retrieve an article by ID from Lexoffice.

Get Contact

Tool to retrieve a specific contact by its ID.

Get Credit Note

Tool to retrieve a credit note by its UUID from Lexoffice.

Get Credit Note Document

Tool to render a credit note document (PDF).

Get Delivery Note

Tool to retrieve a specific delivery note from Lexoffice by its ID.

Get Dunning

Tool to retrieve a dunning document by its ID.

Get Dunning Document

Tool to render and retrieve a dunning document (PDF) reference.

Get Event Subscription

Tool to retrieve a specific event subscription by its ID.

Get Invoice

Tool to retrieve a specific invoice by its UUID.

Get Invoice Document

Tool to render an Invoice Document (PDF) by invoice ID.

Get Order Confirmation

Tool to retrieve a specific order confirmation by its ID.

Render Order Confirmation Document

Tool to render an Order Confirmation Document as PDF.

Get Payment Information

Tool to retrieve payment information for a specific voucher (invoice or credit note) from Lexoffice.

Get Profile

Retrieves the user and company profile information from Lexoffice.

Get Quotation

Tool to retrieve a quotation by its ID.

Get Quotation Document

Tool to render a quotation document as a PDF file.

Get Voucher

Tool to retrieve a specific voucher by its UUID.

List Articles

Tool to list articles from Lexoffice using filters and pagination.

List Contacts

Tool to retrieve all contacts from Lexoffice with optional filters.

List Countries

Tool to retrieve the list of all available countries with tax classifications from Lexoffice.

List Event Subscriptions

Tool to retrieve all event subscriptions for the current access token.

List Payment Conditions

Tool to retrieve list of currently configured payment conditions from Lexoffice.

List Posting Categories

Tool to retrieve the list of posting categories for bookkeeping vouchers (revenue or expense) supported in lexoffice.

List Print Layouts

Tool to retrieve all print layouts for invoices and other documents.

List Recurring Templates

Tool to retrieve all recurring templates from Lexoffice.

List Voucherlist

Tool to retrieve voucherlist from Lexoffice including bookkeeping vouchers (salesinvoices, salescreditnotes), invoices, credit notes, order confirmations, quotations, and delivery notes.

List Vouchers

Tool to filter vouchers by voucher number from Lexoffice.

Update Article

Tool to update an existing article in Lexoffice with new data.

Update lexoffice contact

Tool to update an existing contact in lexoffice.

Upload Voucher File

Tool to upload and assign files (PDF or image) to a specific voucher in lexoffice.

FAQ

Frequently asked questions

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

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

Start with Lexoffice.It takes 30 seconds.

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

Start building