How to Use the Ninehire MCP in Vercel AI SDK

Q: How do I configure the Ninehire MCP Server within a Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client using createMCPClient with your Vinkius HTTP URL. Then, pass the tools from mcpClient.tools() into generateText or streamText to let your LLM interact with candidate data.

Q: What is the correct way to close the connection after fetching job postings?

Always call mcpClient.close() once your stream finishes. This prevents hanging HTTP connections in your serverless functions when calling tools like listjobpostings.

Q: How does Vinkius secure applicant evaluations and profiles when using this integration?

All sensitive candidate evaluations fetched via listcandidateevaluations flow through an ephemeral, zero-trust sandbox using this MCP setup. No personal applicant profiles or scorecards are ever stored on Vinkius disks, keeping your recruitment data isolated and compliant.

Build live-updating recruitment dashboards in Next.js using the Vercel AI SDK and Ninehire.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ninehire MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render live candidate profiles inside Vercel AI SDK

Let your users watch applicant data load in real-time without blank-screen waiting. When your application queries the Ninehire MCP Server, the `get_applicant_profile` tool streams candidate details straight into your React or Next.js components. Edge runtime compatibility means zero cold starts when pulling up resume data. You call `mcpClient.tools()` to grab the applicant endpoints, feed them to `streamText`, and let the Vercel AI SDK render live lists using `list_job_applicants` as the data hits the client.

Instant job posting filters on the edge with this MCP Server

Stop making users wait for heavy backend queries when filtering open roles. This MCP Server lets your Next.js frontend fetch filtered listings instantly via `list_job_postings` based on department or location. Your interface stays responsive because the Vercel AI SDK handles the stream chunk by chunk. Combine `list_organization_departments` with `list_job_locations` to build dynamic, fast-loading search sidebars that update as the user types.

Frictionless candidate registration from any form

Let applicants submit their info and see instant feedback on their application status. By passing the `register_new_applicant` tool to your Vercel AI SDK setup, your chat interface or custom form registers talent without page reloads. Under the hood, the client manages the connection and closes it cleanly with `mcpClient.close()`. You get a snappy, modern application flow that feels like a native app instead of a slow HR portal.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the client using `createMCPClient` with your Vinkius HTTP URL. Then, pass the tools from `mcpClient.tools()` into `generateText` or `streamText` to let your LLM interact with candidate data.

Yes, the server runs in a V8 isolate sandbox, making it lightweight enough for edge environments. You can call tools like `list_job_applicants` and stream the results directly to the browser without hitting execution limits.

Vinkius handles the authorization layer so you only need a single endpoint token. You don't have to manage complex headers or OAuth flows inside your Next.js code when calling `get_authenticated_user_info`.

Always call `mcpClient.close()` once your stream finishes. This prevents hanging HTTP connections in your serverless functions when calling tools like `list_job_postings`.

All sensitive candidate evaluations fetched via `list_candidate_evaluations` flow through an ephemeral, zero-trust sandbox using this MCP setup. No personal applicant profiles or scorecards are ever stored on Vinkius disks, keeping your recruitment data isolated and compliant.

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