How to Use the Lexware Office (Accounting & Invoicing) MCP in Vercel AI SDK

Q: How do I stream Lexware Office (Accounting & Invoicing) tools using Vercel AI SDK?

Install ai and @ai-sdk/mcp, then initialize the client with createMCPClient targeting the Vinkius URL. Feed mcpClient.tools() into streamText and close the connection when done.

Q: Can I use Vercel AI SDK to filter German tax categories via this MCP Server?

Yes. The model uses listpostingcategories to match expenses with correct DATEV codes. This happens dynamically within your streaming text function.

Q: How do I handle pagination when listing Lexoffice documents?

The model handles pagination automatically. When calling listinvoices, the server returns paginated datasets that your agent requests in sequence to build a complete list.

Stream real-time German tax and billing data directly into your Next.js frontend using the Vercel AI SDK and our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lexware Office (Accounting & Invoicing) MCP to Vercel AI SDK

Create your Vinkius account to connect Lexware Office (Accounting & Invoicing) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Lexware Office (Accounting & Invoicing) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time UI updates with Vercel AI SDK and MCP Server.

Our MCP Server connects your application directly to Lexoffice data, allowing you to pull transaction records into your Next.js components using `list_vouchers` and `list_invoices`. The Vercel AI SDK streams these records in real-time, eliminating loading spinners. Your users see actual numbers update instantly, showing real billing data without typical API lag.

Fast contact validation on the Edge.

The `create_contact` and `get_contact` tools let your application verify corporate details on the fly during onboarding. Running this check inside Edge Functions means low latency and zero cold starts. Your agent parses user input and immediately creates a record matching German bookkeeping standards.

Live audit tracking in chat interfaces.

The `list_credit_notes` and `list_payment_conditions` tools let you display payment terms and outstanding credits directly in a chat interface. This removes the need to build complex custom tables for every financial view. The raw JSON maps directly to your UI components, updating the view as your agent reasons through the ledger.

Setup guide

Set up Lexware Office (Accounting & Invoicing) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Lexware Office (Accounting & Invoicing) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Lexware Office (Accounting & Invoicing) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lexware Office. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Lexware Office (Accounting & Invoicing) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Lexware Office (Accounting & Invoicing) MCP in Vercel AI SDK

Install `ai` and `@ai-sdk/mcp`, then initialize the client with `createMCPClient` targeting the Vinkius URL. Feed `mcpClient.tools()` into `streamText` and close the connection when done.

Yes. The model uses `list_posting_categories` to match expenses with correct DATEV codes. This happens dynamically within your streaming text function.

Yes, it works directly on the Edge. The client communicates via standard HTTP, meaning your Edge Functions can invoke `get_invoice` without hitting execution limits.

The model handles pagination automatically. When calling `list_invoices`, the server returns paginated datasets that your agent requests in sequence to build a complete list.

All operations involving billing records, customer tax IDs, and financial totals run inside isolated sandboxes. Your API keys are never exposed to the frontend, and Vinkius acts as a secure, ephemeral bridge that does not store your German accounting logs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript