How to Use the Griffin MCP in Vercel AI SDK

Q: How do I set up the Griffin MCP Server with Vercel AI SDK?

Run npm install ai @ai-sdk/mcp to connect the Griffin server to your Vercel AI SDK codebase. Initialize the client using createMCPClient with your HTTP endpoint, then pass the Griffin tools to streamText. Always call mcpClient.close() when the session ends to prevent memory leaks in your Vercel deployment.

Q: How does the Vercel AI SDK handle Griffin account lists?

The Vercel AI SDK calls listaccounts to fetch all bank accounts for a Griffin organization. It streams this array straight to your React components, letting you render account selectors dynamically while the model processes the user's prompt.

Q: Can the Vercel AI SDK retrieve specific Griffin organization data?

Your Vercel AI SDK application can use getorganization to fetch details for a specific Griffin entity. This helps you scope banking actions to the correct corporate client before executing transfers or checking balances.

Q: Is my bank transaction data safe when using Griffin with Vercel AI SDK?

All bank transaction records fetched via gettransaction are processed inside an ephemeral, zero-trust V8 isolate. Vinkius secures your Griffin API keys, meaning sensitive financial records are never logged or stored by the Vercel AI SDK hosting environment.

Stream live bank ledger states and verification checks directly to your React components using 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 Griffin MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render live ledger transactions via Vercel AI SDK

This MCP Server lets your Vercel AI SDK frontend fetch Griffin bank account histories directly. Your Vercel AI SDK client calls `list_transactions` to stream Griffin ledger entries in real time. You don't have to build custom API endpoints or handle complex polling logic in Next.js. The Griffin server returns raw transaction data that feeds straight into your Vercel AI SDK components. By using `get_account`, your Vercel AI SDK application can display updated balances alongside the transaction list, giving your users an instant look at their money moves.

Real-time KYC verification status updates

This MCP Server exposes Griffin identity verification checks directly to your Vercel AI SDK edge functions. Your Vercel AI SDK UI can pull the latest status using `get_verification` to show users exactly where they stand in the onboarding pipeline. Instead of staring at a static spinner, your Vercel AI SDK interface updates live as the Griffin background checks complete. You query `list_verifications` to check multiple submissions at once, updating the React state on the fly as Griffin processes the compliance data.

Execute internal transfers with instant feedback

This MCP Server handles Griffin money movement directly from your Vercel AI SDK chat interfaces. When a user requests a balance shift, the Vercel AI SDK triggers `create_internal_transfer` to move funds between Griffin accounts instantly. The transfer status streams back to your Vercel AI SDK UI immediately. You can catch errors or confirmation payloads on the edge, updating the user's view the millisecond Griffin registers the transaction.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` to connect the Griffin server to your Vercel AI SDK codebase. Initialize the client using `createMCPClient` with your HTTP endpoint, then pass the Griffin tools to `streamText`. Always call `mcpClient.close()` when the session ends to prevent memory leaks in your Vercel deployment.

Yes, the Vercel AI SDK supports running Griffin tools on the edge. The `get_me` tool quickly checks your authenticated user status with minimal latency during edge execution. Because the Vinkius server runs in a sandbox, your Vercel AI SDK edge functions remain secure and fast.

The Vercel AI SDK calls `list_accounts` to fetch all bank accounts for a Griffin organization. It streams this array straight to your React components, letting you render account selectors dynamically while the model processes the user's prompt.

Your Vercel AI SDK application can use `get_organization` to fetch details for a specific Griffin entity. This helps you scope banking actions to the correct corporate client before executing transfers or checking balances.

All bank transaction records fetched via `get_transaction` are processed inside an ephemeral, zero-trust V8 isolate. Vinkius secures your Griffin API keys, meaning sensitive financial records are never logged or stored by the Vercel AI SDK hosting environment.

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