How to Use the Argyle MCP in Vercel AI SDK

Q: How do I initialize the Argyle MCP Server in Vercel AI SDK?

Install @ai-sdk/mcp and ai. Create a client using createMCPClient with your Vinkius HTTP endpoint, then pass mcpClient.tools() to your generateText or streamText function. Remember to close the client connection when the execution completes.

Q: Can I stream Argyle user creation inside Vercel AI SDK?

Yes. When your agent calls createuser, the Vercel AI SDK streams the status updates and user ID directly to your React components. This lets you show progress bars or loading states in real time without polling.

Q: How does Vercel AI SDK handle Argyle OAuth connections?

You use the authProvider option inside createMCPClient to manage user tokens safely. The SDK passes the required credentials to Vinkius, which handles the secure handshake with Argyle's APIs.

Q: What is the best way to handle multiple payroll queries?

Group your tool calls inside streamText. The agent can invoke getincome and listpayouts in parallel, letting the UI render the breakdown as soon as the first chunk of data arrives.

Stream real-time Argyle payroll and employment data directly into your Next.js frontend 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 Argyle MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live employment verifications to your UI

This MCP Server exposes `get_employment` to let your application fetch verified work history on the fly. Your users don't want to stare at a spinner while waiting for income checks. By passing this tool to your streaming text generation, the agent pulls the record and displays the details live as they arrive. You set up the client, call `create_user` to kick off the onboarding flow, and watch the UI update instantly. The combination of Vercel AI SDK and our managed gateway means zero lag between the API fetch and the customer's screen.

Instantly map income breakdowns in Edge Functions

This MCP Server lets your Edge routes query `get_income` and `list_payouts` without loading massive libraries. Running payroll checks at the edge requires speed and zero overhead. The agent processes the raw numbers and outputs a clean breakdown directly to the streaming response. You initialize the connection with `createMCPClient` and pass the tool definitions directly to `streamText`. Once the run finishes, you call `mcpClient.close()` to keep your edge execution times clean and cost-effective.

Validate user identities via Vercel AI SDK tools

By exposing `get_account_check` and `list_identities` to your LLM, this MCP Server lets your model guide users through connection issues in real time. Verification workflows fail when users get stuck on connection steps. It checks if their payroll account is linked and tells them exactly what to do next. You don't have to write custom UI states for every failure scenario. The model handles the logic, queries the status, and streams the resolution steps directly to the frontend.

Setup guide

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

Install `@ai-sdk/mcp` and `ai`. Create a client using `createMCPClient` with your Vinkius HTTP endpoint, then pass `mcpClient.tools()` to your `generateText` or `streamText` function. Remember to close the client connection when the execution completes.

Yes. When your agent calls `create_user`, the Vercel AI SDK streams the status updates and user ID directly to your React components. This lets you show progress bars or loading states in real time without polling.

You use the `authProvider` option inside `createMCPClient` to manage user tokens safely. The SDK passes the required credentials to Vinkius, which handles the secure handshake with Argyle's APIs.

Group your tool calls inside `streamText`. The agent can invoke `get_income` and `list_payouts` in parallel, letting the UI render the breakdown as soon as the first chunk of data arrives.

Yes, all employment records and income data are isolated. Vinkius runs the server in an ephemeral V8 sandbox, ensuring your customers' financial credentials never touch a persistent database or leak to the LLM provider.

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