How to Use the Hubstaff MCP in Vercel AI SDK

Q: Can my Vercel AI SDK app filter Hubstaff projects or users?

Yes. The tools on this MCP server, like listprojects and listusers, accept parameters for filtering. You can prompt your agent to 'get projects for the Phoenix account' and it will pass the correct arguments to the tool.

Q: Is it possible to get a specific user's details from Hubstaff using the Vercel AI SDK?

Absolutely. Your agent can use the getuser tool with a specific user ID. The Vercel AI SDK will then stream that user's details back to your application, which you can then display in your UI.

Stream Hubstaff data directly into your UI. Build live project dashboards in React or Next.js with 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 Hubstaff MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Project Dashboards

Stop showing loading spinners for Hubstaff data. Use the Vercel AI SDK to stream project information directly into your UI components. Your agent can call `list_projects`, and your users will see the project list populate in real time, line by line. From there, you can build drill-down views. When a user clicks a project, your agent uses `get_project` and `list_tasks` to instantly stream the details. It's a much better user experience than waiting for a full API response to load.

Real-time Activity Feeds with the AI SDK

Give managers a live look at what's happening. The Hubstaff MCP Server lets your agent access the `list_activities` tool, and the AI SDK streams the results straight to your frontend. You can build a feed that updates the second a new activity is logged. Combine it with `get_user` to attach names and faces to the activity. Because the data streams, the dashboard feels alive. It’s the kind of feature that makes an internal tool feel indispensable, not clunky.

Stream Timesheet Data for Invoicing

Build a client invoicing or internal payroll app that feels fast. When your agent calls `list_time_entries`, the data doesn't arrive in one big, slow chunk. It streams in, entry by entry, directly into your React or Svelte components. This means you can render data as it arrives, showing progress immediately. Your app can start calculating totals or flagging entries without waiting for the entire dataset. It's how you build modern, responsive financial tools on top of Hubstaff.

Setup guide

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

First, connect your client to the Hubstaff MCP endpoint. Then, in your Next.js or React app, call `generateText` or `streamText` and pass it tools like `list_projects` and `list_activities`. The AI SDK handles streaming the tool output directly into your UI components.

Yes. The tools on this MCP server, like `list_projects` and `list_users`, accept parameters for filtering. You can prompt your agent to 'get projects for the Phoenix account' and it will pass the correct arguments to the tool.

Vinkius handles the server-side auth for you. You just need the single MCP endpoint token provided by Vinkius. Your frontend app, built with the Vercel AI SDK, uses this token to securely connect without managing Hubstaff's OAuth flow directly.

Absolutely. Your agent can use the `get_user` tool with a specific user ID. The Vercel AI SDK will then stream that user's details back to your application, which you can then display in your UI.

Your connection to the MCP Server is encrypted via HTTPS. When you use a tool like `list_time_entries`, the data streams from our secure environment directly to your user's browser. It's your responsibility to handle that data securely on the frontend, but it is never stored on our servers.

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