How to Use the intelliHR MCP in Vercel AI SDK

Q: Can I filter active positions in Vercel AI SDK using intelliHR tools?

Yes, you feed listpositions to your generation function. The model filters the results based on user prompts and streams the structured list of active job titles directly to the client.

Q: How does this MCP Server handle large team directories?

The server paginates requests through listpeople to prevent memory issues. Your agent requests records in manageable batches, keeping your Next.js Edge Functions fast and light.

Q: Is employee remuneration data safe when using Vercel AI SDK?

Your sensitive payroll data fetched via listremuneration passes through an isolated V8 sandbox on Vinkius. No data is stored on our servers, and the transmission to your Next.js application uses secure TLS encryption.

Populate real-time HR dashboards using Vercel AI SDK to stream intelliHR employee records directly into your React frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect intelliHR MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed real-time directory lookups to your UI

The `list_people` tool exposes employee records directly to your Vercel AI SDK application, letting users query personnel files without waiting for slow API responses. Your frontend receives chunks of user data as they stream from this MCP Server, rendering team profiles instantly. You configure the client to request specific fields like job roles or office locations. By calling `get_person`, the agent pulls deep profiles and displays them in your UI components before the final model output completes.

Map organizational hierarchies on the fly

The `list_positions` and `list_jobs` tools let your frontend app trace reporting lines and job levels dynamically. When a user asks your Vercel AI SDK chatbot about team structures, the model fetches active roles and updates the UI state in real-time. This setup avoids stale database lookups by hitting the live HR API directly. Your interface stays updated with active titles and role definitions from this MCP Server without manual synchronization scripts.

Audit pay rates securely via Vercel AI SDK

The `list_remuneration` and `list_training` tools pull pay structures and professional development histories straight into your UI. Your Vercel AI SDK client renders these financial and training logs as they arrive, avoiding loading spinners. Security remains tight because Vinkius handles the underlying credentials. Your React or Next.js frontend simply receives the clean data stream, letting managers audit salaries and training compliance safely.

Setup guide

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

You initialize the MCP client in your route handler and pass the tools directly to `streamText`. The model uses `list_people` to pull records and streams the JSON chunks directly to your React components.

Yes, you feed `list_positions` to your generation function. The model filters the results based on user prompts and streams the structured list of active job titles directly to the client.

Here is the thing: Vinkius manages the credentials so your Vercel AI SDK code only needs a single endpoint token for the MCP Server. You pass this token in the client configuration to authenticate all requests.

The server paginates requests through `list_people` to prevent memory issues. Your agent requests records in manageable batches, keeping your Next.js Edge Functions fast and light.

Your sensitive payroll data fetched via `list_remuneration` passes through an isolated V8 sandbox on Vinkius. No data is stored on our servers, and the transmission to your Next.js application uses secure TLS encryption.

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