How to Use the Everhour Time Tracking MCP in Vercel AI SDK

Q: How do I stream active timer data using Everhour Time Tracking and Vercel AI SDK?

Use the getcurrentlyrunningtimer tool inside your streamText call via the MCP client. The SDK streams the active task details directly to your React components, letting you build live-updating status bars without writing manual polling loops.

Q: How does this tool list project tasks without slowing down the UI?

The listprojecttasks tool sends clean JSON payloads from the server. The SDK streams this data chunk-by-chunk, allowing your frontend to render the task list as it arrives.

Stream real-time project timers and team hours directly to your React or 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 Everhour Time Tracking MCP to Vercel AI SDK

Create your Vinkius account to connect Everhour Time Tracking 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 Everhour Time Tracking with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live timer streaming with Vercel AI SDK

The `get_currently_running_timer` tool lets your Vercel AI SDK application check active timers instantly through our MCP connection. Your frontend streams the exact task name and start time straight to the user interface, bypassing slow intermediate API endpoints. By integrating this tool with `streamText`, you bypass standard page reloads. Users watch their active tracking status update in real-time as the model feeds the raw Everhour payload directly into your custom UI components.

Budget tracking on Edge Functions

The `list_projects_within_budget` tool inspects your project financial limits directly from an edge runtime. Because this MCP Server runs in a secure sandbox, your AI client pulls live budget metrics without bloat. Combine this with `get_project_detailed_data` to build light dashboards that run on the edge. The Vercel AI SDK renders these financial metrics dynamically, warning team leads before projects cross budget thresholds.

Instant team hours auditing

The `quick_time_tracking_audit` tool analyzes recent team entries to find tracking gaps. Your agent runs this audit and streams structured summaries directly into your Next.js dashboard. You can pair this with `list_team_time_records` to let managers query team logs through chat. The Vercel AI SDK handles the data stream, printing clean tables of hours worked as soon as the model processes the raw dates.

Setup guide

Set up Everhour Time Tracking 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 Everhour Time Tracking 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 Everhour Time Tracking 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 Everhour Time Tracking. 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 Everhour Time Tracking 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 Everhour Time Tracking MCP in Vercel AI SDK

Use the `get_currently_running_timer` tool inside your `streamText` call via the MCP client. The SDK streams the active task details directly to your React components, letting you build live-updating status bars without writing manual polling loops.

Yes. This MCP Server runs on Vinkius, meaning your edge functions make lightweight HTTP requests to fetch time data. You can run tools like `list_tracked_projects` directly on the edge without hitches.

Pass your Vinkius endpoint token to connect the MCP Server. The SDK manages the secure connection, so your agent can safely call `get_everhour_user_metadata` without exposing raw API keys to the client side.

The `list_project_tasks` tool sends clean JSON payloads from the server. The SDK streams this data chunk-by-chunk, allowing your frontend to render the task list as it arrives.

Your time logs, project budgets, and member roles stay secure. Vinkius runs this server in an isolated sandbox, meaning your raw Everhour data is processed on-the-fly without persistent storage.

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