How to Use the Humaans MCP in Vercel AI SDK

Q: How do I stream Humaans employee lists using Vercel AI SDK?

Initialize the client with createMCPClient using an HTTP transport pointed at your Vinkius MCP endpoint. Pass the tools from mcpClient.tools() into streamText to let your LLM call listemployees and render the results live.

Q: How does Vercel AI SDK handle authentication for Humaans?

You configure the authProvider in your client setup to inject the Humaans token. The Vercel AI SDK then passes this token securely through the MCP gateway, ensuring no raw credentials leak to the browser.

Q: What happens if a user requests a document list?

The AI client calls listdocuments through the gateway. The SDK streams the document metadata directly to your UI components, allowing immediate downloads of company policies.

Q: How does this setup protect sensitive Humaans employee data?

Your personnel data, including salary roles from listroles and private files from listdocuments, never persists on Vinkius servers. The connection uses ephemeral V8 sandboxes that encrypt all transit payloads, keeping your personnel records isolated from external storage.

Stream Humaans HRIS data directly into your React components with 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 Humaans MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Employee Directory Queries

The `list_employees` and `get_employee` tools let your Vercel AI SDK client fetch active Humaans staff directories and profile specifics instantly. Instead of making users wait for a full page reload, the raw Humaans JSON payload streams directly into your Next.js frontend, rendering clean UI cards as the data arrives. You configure `createMCPClient` on your Vercel Edge Functions to trigger these Humaans calls the second a manager asks for team details. When the query finishes, call `mcpClient.close()` to keep your serverless execution times tight while pulling Humaans directory updates.

Real-time Leave Calendars via Vercel AI SDK

The `list_leaves` and `list_public_holidays` tools feed direct Humaans calendar data to your Vercel AI SDK streaming interface. Your AI client parses these Humaans endpoints to build interactive time-off timelines on the fly, showing exactly who is out of the office this week. Because the Vercel AI SDK handles streaming text outputs, your users watch the Humaans schedule build out day-by-day in their chat window. You don't need heavy state management libraries because the raw Humaans API responses map straight to your React component props.

Instant Org Structure Visualization

The `list_departments`, `list_teams`, and `list_offices` tools map your entire Humaans organizational hierarchy. Your Vercel AI SDK client calls these endpoints to draw clean SVG org charts directly in the chat interface as the user asks about internal reporting structures. Using this MCP Server ensures you don't expose your master Humaans API key to the browser. Secure backend fetching coordinates the process, meaning your sensitive internal Humaans team lists stay protected behind your server-side endpoint.

Setup guide

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

Initialize the client with `createMCPClient` using an HTTP transport pointed at your Vinkius MCP endpoint. Pass the tools from `mcpClient.tools()` into `streamText` to let your LLM call `list_employees` and render the results live.

Yes, this server runs on edge runtimes without cold-start delays. Just ensure you invoke `mcpClient.close()` at the end of the edge execution block to prevent hanging network connections.

You configure the `authProvider` in your client setup to inject the Humaans token. The Vercel AI SDK then passes this token securely through the MCP gateway, ensuring no raw credentials leak to the browser.

The AI client calls `list_documents` through the gateway. The SDK streams the document metadata directly to your UI components, allowing immediate downloads of company policies.

Your personnel data, including salary roles from `list_roles` and private files from `list_documents`, never persists on Vinkius servers. The connection uses ephemeral V8 sandboxes that encrypt all transit payloads, keeping your personnel records isolated from external storage.

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