How to Use the DeskTime MCP in Vercel AI SDK

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

First, npm install ai @ai-sdk/mcp. Then, use createMCPClient with your Vinkius URL. You pass the tools from mcpClient.tools() into the generateText or streamText functions.

Q: Can I build a live team status board with DeskTime and the Vercel AI SDK?

Yes. Your agent can call the listonlinestaff tool within a streamText function. This lets you stream the list of active employees directly into a React component for a live-updating display.

Q: What project management features can I build with the Vercel AI SDK and DeskTime?

You can build a UI that lets an agent createproject, createnewtask, and marktaskcompleted. Because you're using the AI SDK, the UI can update instantly as the agent confirms the actions.

Build live-updating dashboards for DeskTime with the Vercel AI SDK. Stream project status and team productivity directly into your React components.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeskTime MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Project Data Directly to Your UI

This MCP server gives you tools to manage projects and tasks. With the Vercel AI SDK, you don't just call a function and wait. When your agent uses `create_new_task` or `mark_task_completed`, the results can stream directly into your UI, updating your app in real time without a full page reload. You can build a complete project management interface. Let your users ask the AI to show them everything, and watch as `list_projects` and `list_project_tasks` populate the screen, token by token. It’s a much better experience than staring at a loading spinner.

Build a Real-Time Company Dashboard

Keep a constant pulse on your team's activity. The `list_online_staff` tool tells you exactly who is working right now. You can hook this up to `streamText` and build a live status board that updates automatically. Combine that with performance data. Your agent can use `get_employee_performance` to fetch productivity scores and `get_productivity_reports` for a wider view. Since you're using the AI SDK, this data can flow right into your charts and graphs as it arrives.

Get Company Details on Demand

Pulling static information is just as straightforward. Your agent can use the `get_company_info` tool to fetch basic details about your DeskTime account or `get_project_details` to get the specifics on a single project. This is perfect for building admin panels or summary views. You can create a component that lets a user select a project, and your agent will use the DeskTime tools to fetch and display all the relevant information right inside your application.

Setup guide

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

First, `npm install ai @ai-sdk/mcp`. Then, use `createMCPClient` with your Vinkius URL. You pass the tools from `mcpClient.tools()` into the `generateText` or `streamText` functions.

Yes. Your agent can call the `list_online_staff` tool within a `streamText` function. This lets you stream the list of active employees directly into a React component for a live-updating display.

You can build a UI that lets an agent `create_project`, `create_new_task`, and `mark_task_completed`. Because you're using the AI SDK, the UI can update instantly as the agent confirms the actions.

It does. The HTTP transport is fully compatible with the edge runtime. Your agent can fetch DeskTime data with low latency, close to your users.

This server only processes your DeskTime project, task, and employee productivity data for each request. Vinkius runs every tool call in a new, sandboxed environment that is destroyed immediately after. Your data is never stored.

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