How to Use the Dext MCP in Vercel AI SDK

Q: How do I connect the Dext MCP server to my Vercel AI SDK project?

You'll use the createMCPClient function from the @ai-sdk/mcp package. Point the transport URL to the Vinkius endpoint you were given. Then you can pass the tools from mcpClient.tools() directly to generateText.

Q: Can I show a list of receipts pending review from Dext in my Vercel AI SDK app?

Yes. Your agent can call the listitemspendingreview tool. Since you're using the Vercel AI SDK, you can stream the results directly into a UI component to show a live-updating list.

Q: What's the best way to get Dext invoice details with the Vercel AI SDK?

Have your agent use the getitemdetails tool with the specific item's ID. This will fetch all the detailed information for that invoice. You can then display it in a modal or a detail view in your application.

Connect Dext to your Vercel AI SDK app and stream live invoice data directly into your UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dext MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Real-Time Dashboards

Your users don't want a loading spinner. With the AI SDK, you can stream results from Dext's API right into your React or Svelte components. Use `list_inbox_items` and watch the table populate line by line as the data arrives. This isn't just for lists. You can build a live status view for a single invoice using `get_item_details`, updating the UI as your agent processes it. It gives users immediate feedback that their accounting is being handled.

Interactive Client Management

Let your users manage their own accounting clients directly from your app. The Vercel AI SDK can call `list_accounting_clients` and render the results instantly. No page reloads, just a clean, fast interface. You can even build a component that pulls `list_account_users` to show who has access, or `list_connected_bank_accounts` to verify data sources are active. This is how you build a self-service portal, not just a static report.

Instant Search for Vercel AI SDK

Add a search bar to your app that feels instant. When a user types, your agent can use `search_inbox_by_keyword` on the Dext MCP Server. The results stream back and update the UI in real time. Combine this with `list_extracted_suppliers` to create a powerful autocomplete feature. As the user types a supplier name, you can offer suggestions pulled directly from their processed documents.

Setup guide

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

You'll use the `createMCPClient` function from the `@ai-sdk/mcp` package. Point the transport URL to the Vinkius endpoint you were given. Then you can pass the tools from `mcpClient.tools()` directly to `generateText`.

Yes. Your agent can call the `list_items_pending_review` tool. Since you're using the Vercel AI SDK, you can stream the results directly into a UI component to show a live-updating list.

Have your agent use the `get_item_details` tool with the specific item's ID. This will fetch all the detailed information for that invoice. You can then display it in a modal or a detail view in your application.

It does. The Vinkius MCP transport is HTTP-based and fully compatible with the Edge runtime. You can build fast, serverless accounting tools this way.

Your agent's requests to Dext are proxied through Vinkius's ephemeral sandboxes. The server only handles receipt, invoice, and supplier data, and each request is isolated. Your Vinkius token is the only key; the server itself stores nothing.

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