How to Use the Breezy HR MCP in Vercel AI SDK

Q: How do I connect Breezy HR to my Vercel AI SDK app?

Use the MCP client transport. Install @ai-sdk/mcp, set up the HTTP connection to your Vinkius endpoint, and pass the tools directly to streamText. Don't forget to call close() when the session ends.

Q: Can my agent move candidates between stages in real-time?

Yes, by using movecandidate. The agent determines the correct stage ID from liststages and executes the transition, which streams the updated stage status directly to your user's view.

Stream Breezy HR candidate pipelines directly into your Next.js frontend in real-time using 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 Breezy HR MCP to Vercel AI SDK

Create your Vinkius account to connect Breezy HR 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 Breezy HR with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live candidate tracking via Vercel AI SDK

Stop making your users wait for slow API responses. When your agent fetches candidate lists with `list_candidates` or updates their status using `move_candidate`, the Vercel AI SDK streams those updates straight to the browser. Your React components render the pipeline changes frame by frame as the data arrives from Breezy HR. You do not need loading spinners or complex polling setups anymore. By pulling stage configurations with `list_stages`, the UI updates instantly. Your users watch their recruitment board change in real-time, making the interface feel fast and responsive.

Real-time position creation with this MCP Server

Building a dashboard to open new roles requires instant feedback. This MCP Server lets your application use `create_position` to spin up job listings and push them straight to your UI. The Vercel AI SDK handles the stream, so the new role shows up on screen the millisecond Breezy HR confirms it. It pulls metadata like company profiles via `get_company` and displays them next to the newly created role. You get a clean, reactive flow where users can check all openings using `list_positions` without a single page refresh.

Instant candidate profiles without loading states

When an agent matches a resume and runs `create_candidate`, you want that profile visible immediately. The SDK hooks into the stream so recruiters see the candidate's details pop up on their screen while the AI agent is still processing the resume. The agent can fetch specific records with `get_candidate` or pull down onboarding checklists using `list_task_templates`. Because everything streams over a single connection, the interface stays lightweight and fast.

Setup guide

Set up Breezy HR 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 Breezy HR 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 Breezy HR 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 Breezy HR. 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 Breezy HR 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 Breezy HR MCP in Vercel AI SDK

Use the MCP client transport. Install `@ai-sdk/mcp`, set up the HTTP connection to your Vinkius endpoint, and pass the tools directly to `streamText`. Don't forget to call `close()` when the session ends.

Yes, this setup is built for edge runtimes. The Vercel AI SDK connects to the Breezy HR MCP Server via lightweight HTTP transport, avoiding heavy node-only dependencies. Your API routes will stay fast and cold-starts won't be an issue.

The SDK passes your requests directly through the managed Vinkius gateway. If you hit Breezy HR limits while running `list_candidates`, the server returns standard error codes that your frontend can catch and display gracefully.

Yes, by using `move_candidate`. The agent determines the correct stage ID from `list_stages` and executes the transition, which streams the updated stage status directly to your user's view.

Your recruitment data never sits on a persistent database. Vinkius runs the Breezy HR integration inside isolated, ephemeral V8 sandboxes that self-destruct after execution. Candidate details and job specifications are only held in memory during the active API stream.

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