How to Use the ATS Anywhere MCP in Vercel AI SDK

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

Install @ai-sdk/mcp and ai via npm. Initialize the client using createMCPClient with the Vinkius HTTP URL. Pass the tools directly into streamText to let your LLM run queries.

Q: How does the ATS Anywhere MCP integration with Vercel AI SDK handle OAuth?

You pass your token using the authProvider option in createMCPClient. This ensures every request to list company sites via listsites is fully authorized. Your users won't need to manage raw API keys in the frontend code.

Q: How does this server secure applicant notes and candidate profiles?

All candidate records, recruiter notes retrieved via getapplicantnotes, and job details remain inside the Vinkius V8 sandbox. No hiring data is stored or cached on intermediate servers. Your Next.js edge function reads the data stream directly through encrypted transport.

Stream real-time applicant data directly into your Next.js frontend 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 ATS Anywhere MCP to Vercel AI SDK

Create your Vinkius account to connect ATS Anywhere 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 ATS Anywhere with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream applicant profiles instantly to your UI

The `get_applicant` tool lets your Vercel AI SDK application pull complete candidate profiles through this MCP Server. By fetching this data on demand, your interface avoids static loading states and displays candidate details immediately. You feed these results directly into `streamText` to render candidate pipelines on the edge. Because it supports edge runtimes, your recruiters see applicant updates live without page refreshes.

Build live job posting boards on the edge

The `create_job` tool writes new openings directly to your hiring pipeline from any custom React form. Your AI client processes the user's plain text input, extracts the core requirements, and hits the endpoint to publish the listing. This setup works with `list_jobs` to keep your internal boards in sync. Vercel AI SDK handles the stream so your team sees new postings appear as the AI generates them.

Audit recruiter access with this MCP Server

The `list_users` tool exposes your entire recruiter and admin directory to your LLM application. Your application checks who has access to specific listings and candidates without manual database queries. You initialize this connection with `createMCPClient` and pass the tools directly to your model. Remember to call `mcpClient.close()` when the edge execution finishes to prevent hanging connections.

Setup guide

Set up ATS Anywhere 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 ATS Anywhere 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 ATS Anywhere 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 ATS Anywhere. 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 ATS Anywhere 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 ATS Anywhere MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai` via npm. Initialize the client using `createMCPClient` with the Vinkius HTTP URL. Pass the tools directly into `streamText` to let your LLM run queries.

Yes, you can filter them before passing them to the model. Call `mcpClient.tools()` and map over the array to expose only `list_applicants` or `get_applicant_notes`. This keeps your LLM focused on specific recruiting tasks.

You pass your token using the `authProvider` option in `createMCPClient`. This ensures every request to list company sites via `list_sites` is fully authorized. Your users won't need to manage raw API keys in the frontend code.

No, it runs entirely serverless. The Vinkius endpoint handles the connection. Your Next.js edge route simply connects to the MCP Server, runs `get_account_check`, and closes.

All candidate records, recruiter notes retrieved via `get_applicant_notes`, and job details remain inside the Vinkius V8 sandbox. No hiring data is stored or cached on intermediate servers. Your Next.js edge function reads the data stream directly through encrypted transport.

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