How to Use the TrackingTime MCP in Vercel AI SDK

Q: How does TrackingTime integrate with Vercel AI SDK?

The MCP Server exposes tools like starttimer and listtimeentries. Because you're using the Vercel AI SDK, these results stream directly into your UI as they execute. You see the data appear in real-time.

Q: Can I see my tasks in real-time using TrackingTime and Vercel AI SDK?

Absolutely. You can use listtasks to fetch the current task list, and since the data streams into your frontend via the Vercel AI SDK, you'll see updates live as they happen.

Q: Does MCP Server support complex time calculations?

The server provides mechanisms for tracking time through starttimer and stoptimer. It records raw entries that you then display in your application's UI.

Q: What if I want to modify a project using TrackingTime and Vercel AI SDK?

You can use the updatetask tool. This lets your agent change task details, keeping your workflow current without needing manual database writes.

See time data stream live in your Next.js app 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 TrackingTime MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Time Tracking with Vercel AI SDK

When you hit 'start,' the agent calls `start_timer`. You don't wait for a loading spinner; your UI gets updated instantly as the tool result streams into React. This makes time tracking feel native and immediate. The MCP Server exposes functions like `list_time_entries` and `add_time_entry`, letting you display live data updates in components. It’s perfect for showing users exactly how much time they've logged against a project.

Building Project Management Tools with MCP Server

Need to list what projects exist? Just call `list_projects` and the data streams right into your frontend. You can then pass that list to `create_task` or use it to populate a dropdown menu in Svelte. This pattern lets you build entire dashboards. Get project lists, check customer names via `list_customers`, and dynamically update task status using `update_task`.

User Profile Retrieval for Vercel AI SDK

To know who's using the tool, your agent calls `get_user_profile`. You get basic user data that you can display right in the corner of the screen. It’s simple and fast. If you need to manage teams, `list_workspace_users` pulls team member details directly into your client-side state. This makes it easy to scope who can see what time logs.

Setup guide

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

The MCP Server exposes tools like `start_timer` and `list_time_entries`. Because you're using the Vercel AI SDK, these results stream directly into your UI as they execute. You see the data appear in real-time.

This MCP Server handles time logs and project metadata. Specifically, it deals with user names (`get_user_profile`), project identifiers (`list_projects`), and manually entered time records (`add_time_entry`).

Absolutely. You can use `list_tasks` to fetch the current task list, and since the data streams into your frontend via the Vercel AI SDK, you'll see updates live as they happen.

The server provides mechanisms for tracking time through `start_timer` and `stop_timer`. It records raw entries that you then display in your application's UI.

You can use the `update_task` tool. This lets your agent change task details, keeping your workflow current without needing manual database writes.

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