How to Use the ClickTime MCP in Vercel AI SDK

Q: How do I stream ClickTime project lists to my frontend with the Vercel AI SDK?

You install the @ai-sdk/mcp package and connect it to the Vinkius endpoint using createMCPClient. From there, pass the tools returned by the client into streamText to let your agent call listclicktimeprojects and render the results live.

Q: How do I pass user credentials to ClickTime through the Vercel AI SDK?

You use the SDK's authProvider to pass the user's OAuth token dynamically during the session. This ensures that when the agent calls getmyclicktimeprofile, it only accesses the specific workspace data authorized by that user.

Feed live ClickTime reports and project lists into your Next.js app in real-time 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 ClickTime MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Live ClickTime Reports with Vercel AI SDK

Your users don't want to wait for a loading spinner while your LLM fetches thousands of hours of historical data. By linking this MCP Server to your UI, you can stream raw timesheet data directly to the user's screen as it arrives. The `get_high_volume_time_report` tool pulls up to 2,500 records in one go, letting your app display live project trends instantly. Because Vercel AI SDK handles UI generation on the fly, your agent can call `list_time_entries` and render a clean, interactive table of billable hours without making the browser freeze. It makes time tracking feel like a native part of your custom dashboard instead of a slow API call.

Dynamic Project and Job Selection

Building a custom timesheet portal requires quick access to active accounts. This MCP toolset lets your agent run `list_clicktime_clients` and `list_clicktime_projects` to populate dropdowns or auto-complete fields for your users as they type. You get clean arrays of job codes and clients that feed directly into your frontend components. When the agent calls `list_clicktime_jobs`, the SDK streams the active code list straight into your React state so users can select their current task without delay.

Instant User Profile Matching

You don't need to hardcode user IDs or build complex auth bridges just to find out who is logging hours. The agent can use `get_my_clicktime_profile` to grab the current user's metadata the second they open your app. Combine that profile check with `list_clicktime_users` to build team dashboards that render on Vercel's edge network. Your frontend gets immediate access to staff lists and active tracking states without extra backend glue.

Setup guide

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

You install the `@ai-sdk/mcp` package and connect it to the Vinkius endpoint using `createMCPClient`. From there, pass the tools returned by the client into `streamText` to let your agent call `list_clicktime_projects` and render the results live.

Yes, this setup is fully compatible with Edge runtimes. Because the server runs in a secure, hosted sandbox on Vinkius, your edge functions stay lightweight while your agent queries `list_time_entries` on demand.

The SDK streams the model's tool calls, which means you can start rendering the UI skeleton while `get_high_volume_time_report` processes. The 2,500 record payload is handled asynchronously, keeping your serverless functions from hitting execution limits.

You use the SDK's `authProvider` to pass the user's OAuth token dynamically during the session. This ensures that when the agent calls `get_my_clicktime_profile`, it only accesses the specific workspace data authorized by that user.

Absolutely. All raw timesheet records, user profiles, and billable hour logs fetched via `list_clicktime_users` are processed inside isolated, ephemeral V8 sandboxes. Your sensitive company hours and client rates never persist on Vinkius servers, keeping your financial records private.

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