How to Use the Marqeta MCP in Vercel AI SDK

Q: How do I connect the Marqeta MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client with the Vinkius HTTP URL. Pass the tools directly into streamText or generateText so your agent can execute calls like createuser and createcard on the fly.

Q: Can my Vercel AI SDK agent handle live Marqeta payment simulations?

Yes, you can use simulateauthorization and simulateclearing inside your chat interface. The agent triggers these sandbox tools directly, allowing you to test transaction flows without leaving your frontend workspace.

Q: How does Vercel AI SDK manage user transitions in Marqeta?

The createusertransition tool lets your agent freeze or close accounts instantly based on user prompts. The Vercel AI SDK streams this state change to your UI, updating the customer's dashboard without a page reload.

Q: What is the fastest way to provision digital wallets?

Call provisionapplepay or provisiongooglepay through your agent. The server returns the necessary cryptographic payloads directly to your frontend, allowing immediate wallet integration.

Render real-time card issuing UI as your Vercel AI SDK client spins up Marqeta cards and processes payments.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqeta MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instant Card Issuing in Your Streaming UI

The `create_card` tool lets your Vercel AI SDK client generate physical or virtual payment cards on demand. You get the card token back immediately, which means your Next.js frontend can render the card layout in real-time while the streaming response is still finishing. No more loading spinners while waiting for a backend response. You pair this with `create_user` to register cardholders on the fly, feeding the raw JSON output directly into your UI components.

Live Funding and Balance Checks on the Edge

The `get_balances` tool pulls real-time ledger balances for any user or business account. Because this MCP Server runs on Vercel's Edge network, your Vercel AI SDK agent checks funds and triggers `create_gpa_order` to top up accounts with zero cold-start latency. You write standard React hooks that listen to these tools as they fire. When a user requests a balance update, the agent fetches the ledger state and updates the UI state in one fluid motion.

Test Transactions with Vercel AI SDK MCP Server

The `simulate_authorization` tool forces a test transaction through the card network to verify your authorization controls. Your Vercel AI SDK client runs these simulations via this MCP Server in your dev environment, letting you see exactly how your UI handles approved or declined transactions. You can test complex flows like `simulate_clearing` and `simulate_reversal` directly from your chat interface. This setup eliminates the need to write manual mock scripts for your payment testing.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate the client with the Vinkius HTTP URL. Pass the tools directly into `streamText` or `generateText` so your agent can execute calls like `create_user` and `create_card` on the fly.

Yes, you can use `simulate_authorization` and `simulate_clearing` inside your chat interface. The agent triggers these sandbox tools directly, allowing you to test transaction flows without leaving your frontend workspace.

The `create_user_transition` tool lets your agent freeze or close accounts instantly based on user prompts. The Vercel AI SDK streams this state change to your UI, updating the customer's dashboard without a page reload.

Call `provision_apple_pay` or `provision_google_pay` through your agent. The server returns the necessary cryptographic payloads directly to your frontend, allowing immediate wallet integration.

Vinkius runs this MCP Server in an isolated V8 sandbox, meaning your API keys, card tokens, and balance data are never stored or exposed. The Vercel AI SDK communicates via secure, encrypted HTTPS endpoints, ensuring payload transit remains completely 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