How to Use the Mercury MCP in Vercel AI SDK

Q: How does the Vercel AI SDK handle Mercury balance streaming?

It uses the MCP client to fetch listaccounts and pipes the chunked response straight to streamText. This bypasses traditional REST endpoints, letting your React components render financial data line-by-line.

Q: Can I use Vercel AI SDK to create a Mercury recipient?

Your application calls createrecipient within a tool-calling block, allowing the SDK to prompt the user for necessary routing and account numbers during the live chat session.

Let your Vercel AI SDK client stream real-time Mercury balances and transactions directly into your React components 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 Mercury MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Mercury balances using Vercel AI SDK

`list_accounts` pulls your current cash position from the API and pipes it straight to the frontend. Your users watch their actual balances populate step-by-step instead of staring at a blank screen. By feeding `get_treasury_balance` directly into `streamText`, the interface updates the moment the ledger changes. This eliminates the need for manual polling or custom webhook setups.

Render instant transaction histories on the edge

`list_transactions` executes inside Edge Functions to fetch ledger entries close to your users. The Vercel AI SDK processes this payload instantly, allowing your UI to render clean tables on the fly. If a user asks about a specific payment, `get_transaction` isolates that single event. The SDK maps this raw JSON directly into your custom React components.

Build interactive recipient setup forms

Initiating a payment setup starts with `create_recipient` inside your streaming UI. The MCP Server handles the token exchange securely, letting users input routing numbers directly inside the chat interface. You can verify existing entries by running `list_recipients` alongside the input fields. This prevents duplicate records and keeps your Mercury dashboard clean.

Setup guide

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

It uses the MCP client to fetch `list_accounts` and pipes the chunked response straight to `streamText`. This bypasses traditional REST endpoints, letting your React components render financial data line-by-line.

Your application calls `create_recipient` within a tool-calling block, allowing the SDK to prompt the user for necessary routing and account numbers during the live chat session.

The SDK directly imports tools from the server instance. This allows operations like `list_statements` to execute as native functions within your streaming generation context.

Yes, this MCP Server runs on a V8 sandbox. This means your Vercel AI SDK code can fetch `get_treasury_balance` or `list_transactions` without hitting Node-specific execution bottlenecks.

Your raw transaction details and bank account balances never touch Vinkius servers or external LLM databases. The SDK communicates directly through an isolated, zero-trust V8 sandbox that handles authentication locally.

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