How to Use the Troops MCP in Vercel AI SDK

Q: How do I check candidate status with Troops and Vercel AI SDK?

You use the getcandidate tool. Your agent pulls up a candidate's details, and because you’re using the Vercel AI SDK, the data streams to your UI in real-time. You won’t wait for any loading state.

Q: Can I process timesheets with Troops when building my application with Vercel AI SDK?

Yep. The submittimesheet tool handles that workflow. When an employee submits hours, the confirmation or error message streams instantly to your frontend. It feels native because you're seeing the action happen live.

Q: Does the Troops server support creating new roles using Vercel AI SDK?

It supports core HR functions like creating a job (createjob) or registering an employee as a candidate (createcandidate). You'll see these actions reflected live in your app.

Q: If I need to list jobs with Troops and Vercel AI SDK, what tools do I use?

You call the listjobs tool. This allows you to filter job offers by status right from your agent code. The resulting array of available positions streams back directly into the user's view.

Display real-time HR data and workflows directly in your UI using 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 Troops MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Candidate Records Live

Use the `create_candidate` tool to register a new person into your system. Your client streams back confirmation instantly, so users see the record appear as it's created. You can also fetch existing data using `get_candidate`. This means when an agent pulls up details for a candidate, the UI updates right then and there, without waiting on a fake loading spinner.

Control Job Offer Lifecycle

The `list_jobs` tool lets you check available job offers. You can filter this list by status so your app only shows what's relevant right now. Need to make a new opening? Use `create_job` to publish an offer, and the result streams back immediately for the user to confirm.

Process Hiring Agreements

Generating legal paperwork is simple. The `generate_contract` tool creates the necessary documents based on inputs. Once the contract exists, you can move straight to closing it out using `sign_contract`. All these steps happen live, providing immediate feedback in your user interface.

Setup guide

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

You use the `get_candidate` tool. Your agent pulls up a candidate's details, and because you’re using the Vercel AI SDK, the data streams to your UI in real-time. You won’t wait for any loading state.

Yep. The `submit_timesheet` tool handles that workflow. When an employee submits hours, the confirmation or error message streams instantly to your frontend. It feels native because you're seeing the action happen live.

This MCP Server primarily handles candidate and job data. Specifically, it touches records related to candidates (e.g., name, status) and details about open jobs.

It supports core HR functions like creating a job (`create_job`) or registering an employee as a candidate (`create_candidate`). You'll see these actions reflected live in your app.

You call the `list_jobs` tool. This allows you to filter job offers by status right from your agent code. The resulting array of available positions streams back directly into the user's view.

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