How to Use the Freshteam MCP in Vercel AI SDK

Q: How do I connect Freshteam to the Vercel AI SDK?

Run npm install ai @ai-sdk/mcp. Use createMCPClient with an HTTP transport pointing to your endpoint. Call mcpClient.tools() and pass the array to streamText.

Q: Can the Vercel AI SDK create Freshteam records?

Yes. The server exposes createemployeerecord for write operations. You control the form inputs in your UI, and the AI formats the API payload to push the new hire into your HRIS.

Q: Does this integration support authentication?

You pass your endpoint token via the authProvider configuration. The server handles the actual API keys behind the scenes. This keeps your frontend secure.

Q: How do I check if the HRIS is online?

Use the checkhrisstatus tool. You can wire this up to a status indicator in your Next.js app to verify the API connection before users try to load employee data.

Build live HR dashboards and automated onboarding flows directly into your React apps 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 Freshteam MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Data to the UI

The `list_employees` and `list_departments` tools let your Vercel AI SDK app pull organizational data straight into your frontend. Instead of users staring at a loading spinner, your React components render the employee directory as the data streams in from the MCP Server. You'll pass these tools directly to `streamText`. When a manager asks for headcount by department, the AI calls the endpoints. The results appear instantly on screen without waiting for the entire payload to resolve.

Vercel AI SDK Candidate Tracking

Calling `list_job_applicants` and `get_applicant_details` fetches candidate profiles from your ATS pipeline. You can build custom interview dashboards where the AI reads resumes and pulls up specific applicant metadata on the fly. Combine this with `get_job_posting_details` to give hiring managers immediate context. They see the job requirements right next to the applicant's experience, all rendered live without page reloads.

Handle Leave Requests and Onboarding

The `list_time_off_requests` and `create_employee_record` tools handle the core operations of your HR system. Your application can review pending PTO or push new hires into the database directly from a chat interface. Since you manage the setup with `createMCPClient`, you control the exact execution flow. The user triggers the action, the AI formats the payload, and your backend handles the write operation.

Setup guide

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

Run `npm install ai @ai-sdk/mcp`. Use `createMCPClient` with an HTTP transport pointing to your endpoint. Call `mcpClient.tools()` and pass the array to `streamText`.

Yes. The server exposes `create_employee_record` for write operations. You control the form inputs in your UI, and the AI formats the API payload to push the new hire into your HRIS.

You pass your endpoint token via the `authProvider` configuration. The server handles the actual API keys behind the scenes. This keeps your frontend secure.

Use the `check_hris_status` tool. You can wire this up to a status indicator in your Next.js app to verify the API connection before users try to load employee data.

The MCP protocol operates in a zero-trust V8 Isolate Sandbox. When `get_applicant_details` reads candidate profiles and resumes, the memory is ephemeral and destroyed immediately after the tool execution completes. Your UI receives the data, but nothing persists in the middleware.

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