How to Use the Mastercard MCP in Vercel AI SDK

Q: How do I add Mastercard tools to my Vercel AI SDK project?

You install the @ai-sdk/mcp package and initialize the client. Then, pass the tools from this MCP Server into streamText or generateText inside your Next.js route handlers. It takes under five minutes to configure.

Q: Can I use Mastercard geolocation tools inside Vercel AI SDK Edge Functions?

Yes, the tools like searchplaces and nearbylocations are fully compatible with edge runtimes. The Vercel AI SDK executes these calls with minimal cold-start overhead, pulling real-time merchant coordinates directly from the Mastercard network.

Q: How does the Vercel AI SDK handle Mastercard fraud reporting?

Your agent uses the submitfraudreport tool within a streaming text session to instantly flag compromised cards. The Vercel AI SDK processes the response payload on your server side, ensuring sensitive transaction details never leak to the client-side bundle.

Get real-time Mastercard card checks and merchant lookups streaming straight into your Next.js frontend with 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 Mastercard MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Card Verification Live with Vercel AI SDK

Stop making users stare at loading spinners while you check their credit card details. This Mastercard MCP Server lets your agent call `validate_account` and stream the status straight to your React UI. You get instant updates on whether a card is active, reducing checkout friction before the user even hits submit. If you need to identify card details without exposing raw numbers to standard logs, your frontend can trigger `bin_lookup` or `bin_lookup_post` in the background. The Vercel AI SDK handles the async stream, updating your form fields with the card category or issuing country as the customer types.

Interactive Merchant Mapping in Next.js

Let your users find nearby physical stores by feeding GPS coordinates directly to your agent. When the user asks where they can buy groceries, your application fires `search_merchants` or `nearby_locations` to scan the Mastercard network. The results stream back as structured JSON, letting you render interactive maps on the fly. Once a store is selected, your agent automatically pulls operational details using `get_merchant` or `get_place_details`. Your Vercel AI SDK setup feeds these details straight into your UI components, showing accepted payment methods and hours without a single page reload.

Instant Fraud Reporting at the Edge

Flag suspicious transactions instantly by running your security agent on Edge Functions. Using this MCP Server, your support team can ask the chat interface to file a report using `submit_fraud_report` directly from their dashboard. The SDK handles the API handshake with Mastercard servers, returning the submission status to your live chat view. To keep your agent sharp, use `merchant_category_codes` and `merchant_industry_codes` to classify transaction types during the review process. This keeps your edge-rendered fraud dashboard accurate and responsive, giving your team immediate visual feedback on active threats.

Setup guide

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

You install the `@ai-sdk/mcp` package and initialize the client. Then, pass the tools from this MCP Server into `streamText` or `generateText` inside your Next.js route handlers. It takes under five minutes to configure.

Yes, the tools like `search_places` and `nearby_locations` are fully compatible with edge runtimes. The Vercel AI SDK executes these calls with minimal cold-start overhead, pulling real-time merchant coordinates directly from the Mastercard network.

Your agent uses the `submit_fraud_report` tool within a streaming text session to instantly flag compromised cards. The Vercel AI SDK processes the response payload on your server side, ensuring sensitive transaction details never leak to the client-side bundle.

The tool returns an error state that your agent catches. You can configure your model to gracefully ask the user to double-check their card details or fall back to manual validation if `validate_account` returns an invalid status.

This MCP Server processes full primary account numbers (PANs) strictly within an ephemeral, zero-trust V8 sandbox. Your Vercel AI SDK backend communicates via encrypted channels, and the server never logs or stores the raw card numbers from `validate_account` or `bin_lookup_post` calls.

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