How to Use the Hurma MCP in Vercel AI SDK

Q: How does Vercel AI SDK handle Hurma custom field mapping?

The model calls listcustomproperties to discover your specific schema. It then maps the incoming UI form data to those custom fields dynamically during the streaming session.

Q: Do I need to manage connection pooling for these HR tools?

No. Always call mcpClient.close() at the end of your execution block to release the connection and avoid leaking resources.

Q: How is our sensitive Hurma candidate and payroll data protected?

The server runs in an isolated V8 sandbox that processes exportovertimes and candidate details entirely in memory. Your API keys are never stored on disk, and all transport layer communication is encrypted.

Feed real-time Hurma HR data directly to your Vercel AI SDK UI using this secure MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hurma MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live HR Dashboards via Vercel AI SDK

The `list_employees` tool pulls your active staff directory directly into your Vercel AI SDK application. This MCP connection lets you fetch records and populate React components dynamically as the user types. Instead of waiting for a slow API payload, the model streams partial JSON directly to the UI. Your users see vacation balances update instantly via `get_vacation_balance` without staring at a blank screen.

Instant Candidate Pipeline Updates

The `create_candidate` tool lets your Vercel AI SDK application insert new applicants directly into your hiring pipeline. Recruiters can paste a resume into a chat window, and the model maps the fields instantly. You can immediately verify the operation by calling `list_vacancy_stages` to show the user exactly where the new applicant sits. This eliminates the lag between data entry and visual feedback.

On-the-Fly Leave Management

The `create_leave_request` tool handles time-off submissions directly from your custom web portal. Your application processes the request, gets the current status, and updates the view immediately. By coupling this with `list_out_of_office`, you build a live calendar view that reflects current team availability. The MCP Server ensures that the view is accurate before they even submit their own request.

Setup guide

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

You initialize the MCP client with your endpoint. Then, pass the tools directly into `streamText` to let the model call `get_employee_details` and render the output chunk by chunk.

Yes. The client is fully compatible with edge runtimes. You can query `list_departments` or fetch candidate profiles with zero cold-start overhead.

The model calls `list_custom_properties` to discover your specific schema. It then maps the incoming UI form data to those custom fields dynamically during the streaming session.

No. Always call `mcpClient.close()` at the end of your execution block to release the connection and avoid leaking resources.

The server runs in an isolated V8 sandbox that processes `export_overtimes` and candidate details entirely in memory. Your API keys are never stored on disk, and all transport layer communication is encrypted.

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