How to Use the Deputy MCP in Vercel AI SDK

Q: How do I stream Deputy roster data using the Vercel AI SDK?

Pass the listactiverosters tool into your streamText function after setting up the HTTP transport. The SDK will handle the raw roster payloads and feed them directly into your UI stream.

Build real-time workforce dashboards that stream live Deputy shift data directly into your Vercel AI SDK frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deputy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Active Shifts into React via Vercel AI SDK

The `list_currently_active_shifts` tool lets your React frontend display real-time clock-in events without making your users wait for a full page reload. By passing this tool from the Vinkius MCP Server directly to `streamText`, you feed live workforce presence data straight into your UI components as the AI processes the raw API response. Your users see names and timestamps pop up on their screens instantly. You bypass the traditional backend polling setup because the SDK handles the incoming data stream directly from the active MCP endpoint.

Manage Leave Requests in Next.js Server Components

The `list_pending_leave_approvals` tool exposes all waiting time-off requests directly to your Vercel AI SDK generative UI context. When a manager asks who is off next week, your LLM calls this endpoint and renders custom interactive approval buttons directly in the chat window. You don't have to build complex form states or handle tedious API routing. The system fetches the raw leave data, structures it, and hands it to your UI component to let managers approve or deny requests on the spot.

Query Workforce Records inside Your AI SDK Chat

The `search_employees_by_name` tool gives your application the power to pull up staff records on demand during live chat sessions. Your user types a partial name, and the Vercel AI SDK client instantly resolves the identity to fetch details via `get_employee_profile`. This integration removes the friction of digging through external payroll or HR databases. You feed the clean profile JSON straight to your streaming text generator, keeping the conversation fast and context-rich.

Setup guide

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

Pass the `list_active_rosters` tool into your `streamText` function after setting up the HTTP transport. The SDK will handle the raw roster payloads and feed them directly into your UI stream.

Yes, the MCP Server runs in a lightweight sandbox on Vinkius, making it fully compatible with Vercel's Edge runtime. Your function simply connects to the endpoint and calls tools like `list_completed_timesheets` without bloating your bundle.

Vinkius manages the API tokens on the backend, meaning your frontend code never exposes sensitive keys. You pass your single Vinkius token when initializing the client, and the SDK safely calls `get_authenticated_user` to verify the session.

The SDK catches transport-level errors and surfaces them as standard stream exceptions. You can wrap your `streamText` call in a standard try-catch block to handle rate limits or API downtime gracefully.

All employee profiles, timesheets, and rosters are processed inside an ephemeral V8 sandbox. The SDK communicates over TLS directly with Vinkius, ensuring sensitive HR data never persists on public servers.

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