How to Use the Fintoc MCP in Vercel AI SDK

Q: How do I stream Fintoc bank movements using the Vercel AI SDK?

You use the listmovements tool within your streaming text generation function. Pass the tools from your MCP client directly to streamText so the agent can fetch and render transaction data in real-time.

Q: Can I trigger Fintoc payment intents directly from a Vercel AI SDK chat interface?

Yes, you can. The agent invokes createpaymentintent when a user requests a transfer, and the response streams back to update the UI state immediately.

Q: How do I handle authentication for Fintoc inside a Vercel AI SDK application?

You configure the createMCPClient method with an authProvider block. This passes the secure token to the MCP Server, keeping your API keys hidden from the client-side code.

Q: Do I need to close the connection after running an MCP tool?

Yes, always call mcpClient.close() when your execution block finishes. This prevents memory leaks in your Edge Functions and keeps your serverless execution times low.

Get real-time bank transactions and payments directly into your React components with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fintoc MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live transaction feeds via Vercel AI SDK

This integration exposes bank ledger data using `list_movements` and `get_movement` to feed your user interface. Your app fetches the latest transaction records and pipes them straight to the front-end stream without waiting for a full page reload. You configure the client to pull the raw financial data and format it inside your UI components. It means users see their bank ledger update line-by-line as the agent processes the feed.

Direct payment initiation in Edge Functions

You initiate bank transfers instantly using `create_payment_intent` and track their status with `get_payment_intent`. Because this MCP Server works with edge-compatible runtimes, your agent can trigger payments instantly during a chat session. The setup handles the payment lifecycle on the fly. Users confirm the amount in the chat window, and your backend executes the transfer immediately, bypassing slow legacy payment gateways.

Automated bank account checks

This server maps financial profiles using `list_accounts`, `get_account`, and `list_subscriptions` to audit user balances. Your AI client reads active subscriptions and current balances to flag payment risks before they happen. By feeding this data directly into your streaming UI, the agent can show users exactly which recurring payments are due. You get clean financial data without writing complex API wrappers.

Setup guide

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

You use the `list_movements` tool within your streaming text generation function. Pass the tools from your MCP client directly to `streamText` so the agent can fetch and render transaction data in real-time.

Yes, you can. The agent invokes `create_payment_intent` when a user requests a transfer, and the response streams back to update the UI state immediately.

You configure the `createMCPClient` method with an `authProvider` block. This passes the secure token to the MCP Server, keeping your API keys hidden from the client-side code.

Yes, always call `mcpClient.close()` when your execution block finishes. This prevents memory leaks in your Edge Functions and keeps your serverless execution times low.

All data passes through a secure V8 isolate sandbox that wipes your session memory the moment the request completes. Your bank credentials and transaction history are never stored or logged on our servers.

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