How to Use the Clockify MCP in Vercel AI SDK

Q: How do I stream live Clockify updates in my Vercel AI SDK application?

Call createMCPClient to connect to the MCP Server, then pass the tools directly to streamText. This lets your agent run addnewtimeentry and stream the status straight to your React frontend.

Q: Can I use Vercel AI SDK to stop active timers on Clockify?

Yes. Your agent invokes stopcurrenttimer through the SDK's tool-calling mechanism. The UI reflects the stopped state instantly without requiring a page refresh.

Q: How does this MCP Server handle multiple user profiles in Vercel AI SDK and Clockify?

The MCP Server uses getmyclockifyprofile to identify the active user. You can pass user-specific tokens via the SDK's auth provider to keep profiles segregated.

Q: Do I need to manually map Clockify projects in my Next.js code?

No. The agent calls listworkspaceprojects automatically when prompted. It then feeds those projects directly to the SDK's text generation function.

Build live Next.js time-tracking UIs that stream real-time Clockify updates 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 Clockify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time UI updates for running timers

Your users see their current timer stop in real-time. By wrapping `stop_current_timer` in Vercel AI SDK's `streamText`, the UI updates the moment the agent executes the call, skipping the usual lag. You get immediate visual confirmation. Because the SDK handles streaming tool results straight to the React frontend, you bypass standard loading spinners while updating Clockify workspaces.

Streaming Clockify workspace data with Vercel AI SDK

Populating dropdowns in your Next.js app shouldn't block your interface. This MCP Server lets your Vercel AI SDK agent fetch lists with `list_clockify_workspaces` and `list_workspace_projects` to render project selectors on the fly. The SDK pipes this data straight to your Edge Functions. Your users get immediate feedback as the agent maps out active clients via `list_workspace_clients` in the background.

Instant time logging from chat inputs

Turn raw user messages into structured log entries. The SDK parses natural language in `streamText` and immediately fires `add_new_time_entry` to post the hours. It keeps the UI responsive. Instead of waiting for a full page reload, the Vercel AI SDK streams the newly created Clockify entry straight into the user's React view.

Setup guide

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

Call `createMCPClient` to connect to the MCP Server, then pass the tools directly to `streamText`. This lets your agent run `add_new_time_entry` and stream the status straight to your React frontend.

Yes. Your agent invokes `stop_current_timer` through the SDK's tool-calling mechanism. The UI reflects the stopped state instantly without requiring a page refresh.

The MCP Server uses `get_my_clockify_profile` to identify the active user. You can pass user-specific tokens via the SDK's auth provider to keep profiles segregated.

No. The agent calls `list_workspace_projects` automatically when prompted. It then feeds those projects directly to the SDK's text generation function.

Your API tokens never touch public client bundles. The SDK executes tool calls like `list_user_time_entries` inside secure Edge Functions, keeping your raw workspace logs 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