How to Use the Altoviz MCP in Vercel AI SDK

Q: How do I connect Altoviz to my Vercel AI SDK project?

Use the @ai-sdk/mcp package to initialize the MCP client with your Vinkius HTTP endpoint. Pass the tools directly into streamText and close the connection when the stream ends.

Q: Can I stream Altoviz invoice data to Next.js using Vercel AI SDK?

Yes, the SDK streams the tool outputs from listsaleinvoices directly to your React components. This avoids blocking UI renders while waiting for the billing API to respond.

Pipe real-time Altoviz invoice and customer data directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Altoviz MCP to Vercel AI SDK

Create your Vinkius account to connect Altoviz 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 Altoviz with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Invoice Streaming with Vercel AI SDK

The `list_sale_invoices` tool lets your Vercel AI SDK client fetch billing records directly into your frontend. By pairing Vercel AI SDK with this Altoviz MCP Server, you feed `list_sale_invoices` directly into your UI components as the LLM fetches them. The SDK handles the streaming chunks while the server grabs the raw invoice metadata. You build a clean, reactive dashboard where customers see their financial records appear line by line.

Instant Customer Profiles on the Edge

The `get_customer_details` tool retrieves customer metadata instantly for your edge functions. Edge functions need to run fast, and this setup doesn't waste milliseconds. When your agent calls `get_customer_details`, the Vercel AI SDK handles the payload on the edge, pulling Altoviz records instantly. You don't have to write custom API wrappers for your Next.js routes.

Interactive Quote and Receipt Renderers

The `list_sale_quotes` and `list_receipts` tools feed business expenses and estimates directly into conversational UI components. Let your users browse their expenses and quotes through a conversational UI. The Vercel AI SDK renders custom React components for these tools the moment the server returns the data. This keeps your frontend highly interactive instead of reading raw JSON dumps.

Setup guide

Set up Altoviz 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 Altoviz 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 Altoviz 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 Altoviz. 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 Altoviz 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 Altoviz MCP in Vercel AI SDK

Use the `@ai-sdk/mcp` package to initialize the MCP client with your Vinkius HTTP endpoint. Pass the tools directly into `streamText` and close the connection when the stream ends.

Yes, the SDK streams the tool outputs from `list_sale_invoices` directly to your React components. This avoids blocking UI renders while waiting for the billing API to respond.

Yes, both the server on Vinkius and the SDK client are fully compatible with edge environments. You can run your billing queries in lightweight edge functions without cold starts.

Vinkius manages the credentials securely on its hosted platform. Your MCP client only needs a single token to access the entire suite of financial tools.

Your customer profiles, quotes, and receipt records are never stored by Vinkius. The MCP client uses ephemeral sandboxes to process the data, ensuring your financial information remains private.

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