How to Use the JobScore MCP in Vercel AI SDK

Feed live candidate pipelines and job descriptions directly into your React components with Vercel AI SDK and the JobScore 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 JobScore MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe applicant profiles directly into your React UI

The `get_candidate` tool pulls contact history, resume highlights, and application stages from your ATS without making the user wait for a page reload. Your Vercel AI SDK application streams these details directly into your component layout as the model finds them. This means recruiters see active profiles appear instantly on screen during live reviews. You bypass the lag of traditional API polling by letting your AI client fetch and render data on the fly.

Build real-time job filters with Vercel AI SDK

The `list_jobs` tool retrieves active listings, departments, and hiring teams directly from your account. By combining this with the Vercel AI SDK, your interface displays open roles dynamically as users type their search queries. Developers get clean TypeScript types for every job post and department. You can render these open positions in Edge Functions to keep latency below 50 milliseconds.

Map recruitment channels on the fly

The `list_sources` tool identifies exactly where your applicants are coming from, whether it is LinkedIn or internal referrals. Your agent calls this endpoint to update your live dashboard charts without blocking the main thread. You configure the client using a clean initialization function to feed these metrics straight into your analytical components. Recruiters spot trends in hiring channels without manually exporting CSV files every morning.

Setup guide

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

You install the core MCP package and instantiate the client with the Vinkius HTTP URL. Pass the tools directly into the tools parameter of your generation functions.

Yes, the server runs in a V8 sandbox on Vinkius, and the Vercel AI SDK client is fully compatible with Edge Functions. This setup avoids cold starts and keeps your recruiting dashboard fast.

Yes, it streams data chunks instantly as they arrive from the API. Your users see candidate names and application stages populate on screen without a single loading spinner.

The SDK manages chunked streaming, but you should write standard backoff rules on your API routes. Vinkius maintains the underlying connection pool to prevent your credentials from hitting thresholds.

Vinkius runs the server in an isolated sandbox, meaning your candidate data and contact histories are never stored on disk. The token handles authorization directly with JobScore, routing data strictly between their API and your secure Vercel deployment.

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