How to Use the HRBlade MCP in Vercel AI SDK

Q: How do I connect HRBlade to my Vercel AI SDK project?

First, install the necessary packages. Then, use createMCPClient and point it to your Vinkius endpoint URL for HRBlade. You can then pass the tools from mcpClient.tools() into generateText or streamText.

Q: Can I build a real-time candidate pipeline with HRBlade and the Vercel AI SDK?

Yes, that's a primary use case. The listcandidates tool combined with the AI SDK's streaming capabilities lets you build a UI where new candidates appear live, without any manual refreshes.

Q: What's the best way to show candidate details using HRBlade and the Vercel AI SDK?

Stream the full list using listcandidates. When a user selects a candidate in your UI, have your agent call getcandidatedetails for that specific ID and stream the results into a detail view.

Q: How do I manage interview templates programmatically?

You can use the listinterviews tool to display all existing templates in your app. To create new ones, just connect a UI form to the createinterview tool.

Build real-time hiring dashboards in your React app. With HRBlade and the Vercel AI SDK, you can stream candidate data right into your UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HRBlade MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instantly Populate Candidate Lists

This MCP server gives you the tools to build a live candidate pipeline. Instead of waiting for a full API response, you can use the Vercel AI SDK to stream results from `list_candidates` directly into your UI components. Your users will see names appearing in the list as they're fetched. From there, clicking a name can trigger a call to `get_candidate_details`. The specific candidate's information streams into a detail pane, creating a fluid, responsive experience without any loading spinners. It feels fast because it is.

Live Interview Tracking in Your App

You can build a dashboard that gives hiring managers a live look at their interview pipeline. Use `list_interviews` to show all the available interview templates. Then, have your agent periodically call `list_interview_responses`. Because you're using the AI SDK, new video responses will pop into the UI the moment they're available. There’s no need to refresh the page. This gives your team a real-time view of who has completed their screening.

Trigger Invites Directly from Your UI

Connect your frontend directly to your hiring workflow. A manager can click a button in your Next.js app to trigger your AI client, which then calls `send_interview_invitation` with the right candidate ID and template. Your UI can show a confirmation message the instant the API call is complete. You can even build an interface for creating new templates by hooking up a form to the `create_interview` tool. It puts the entire interview process right inside your product.

Setup guide

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

First, install the necessary packages. Then, use `createMCPClient` and point it to your Vinkius endpoint URL for HRBlade. You can then pass the tools from `mcpClient.tools()` into `generateText` or `streamText`.

Yes, that's a primary use case. The `list_candidates` tool combined with the AI SDK's streaming capabilities lets you build a UI where new candidates appear live, without any manual refreshes.

Stream the full list using `list_candidates`. When a user selects a candidate in your UI, have your agent call `get_candidate_details` for that specific ID and stream the results into a detail view.

You can use the `list_interviews` tool to display all existing templates in your app. To create new ones, just connect a UI form to the `create_interview` tool.

HRBlade tools process candidate PII, like names and contact info, as well as links to video interviews. Your Vinkius MCP Server runs in an ephemeral sandbox, so data isn't stored. All communication is encrypted end-to-end.

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