How to Use the Modulr MCP in Vercel AI SDK

Q: How does the Vercel AI SDK handle errors during a Modulr transfer?

If a call to modulrcreatepayment fails due to insufficient funds, the error streams to your frontend in real time. Your UI can catch this state instantly and prompt the user to top up their account.

Q: How do I close the connection to the Modulr MCP Server when the page unmounts?

You must call mcpClient.close() inside your cleanup functions. This prevents dangling SSE or HTTP connections in your Vercel AI SDK application.

Run real-time SEPA payouts and spin up virtual accounts directly in 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 Modulr MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live UI streaming for European payouts

Your users won't stare at loading spinners while executing bank transfers. When your React or Next.js app triggers `modulr_create_payment`, the transaction state streams directly into your UI components. This Vercel AI SDK integration keeps the interface alive by piping raw payment status updates from the Modulr MCP Server. It renders immediate feedback as the SEPA or Faster Payment moves from pending to settled.

Instant ledger rendering in Edge Functions

Edge compatibility means you can spin up accounts on the fly. Your agent calls `modulr_create_account` inside a lightweight edge runtime to instantly establish GBP or EUR wallets. The returned ledger details feed right back into the client. By avoiding heavy node environments, your Vercel AI SDK app displays new IBANs to your customers within milliseconds of creation.

Interactive transaction auditing with Vercel AI SDK

Let users query their financial histories using plain English. Your agent runs `modulr_get_transactions` and streams the matching ledger rows directly into a clean UI table. You don't need to write complex polling logic or state management. The Vercel AI SDK handles the stream, letting the Modulr MCP Server drop raw payment logs straight onto the screen.

Setup guide

Set up Modulr 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 Modulr 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 Modulr 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 Modulr Finance. 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 Modulr 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 Modulr MCP in Vercel AI SDK

You configure the Modulr MCP Server with your credentials via Vinkius, and then pass the endpoint token to the client. There is no need to write custom HMAC header signing logic inside your Next.js API routes because the managed server handles it.

Yes, the client works perfectly in Edge Functions. You call `modulr_list_payments` to check bulk transaction arrays without hitting cold starts or exceeding execution limits.

If a call to `modulr_create_payment` fails due to insufficient funds, the error streams to your frontend in real time. Your UI can catch this state instantly and prompt the user to top up their account.

You must call `mcpClient.close()` inside your cleanup functions. This prevents dangling SSE or HTTP connections in your Vercel AI SDK application.

Your IBANs, customer IDs, and transaction logs pass through Vinkius in a secure, ephemeral V8 sandbox. No payment data or bank details are stored on our servers; they transit directly to the banking API.

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