How to Use the LiftedWork MCP in Vercel AI SDK

Q: How do I initialize the LiftedWork client inside Vercel AI SDK?

Install @ai-sdk/mcp to register the MCP Server tools. Use createMCPClient with the Vinkius HTTP endpoint, then pass the tools directly into your generation function.

Q: Do I need to manually close the connection after running a task query?

Always call mcpClient.close() once your MCP session finishes. This prevents connection leaks and keeps your serverless execution environments clean.

Stream live LiftedWork project statuses and client lists directly into your React app 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 LiftedWork MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time project creation in UI

The `create_project` tool builds new workspace containers for job seekers and recruiters directly from the prompt. Your user types a command, and the server instantiates the project while streaming status updates straight to the UI. It's built to bypass slow page reloads, ensuring users see project structures form in real time. The integration uses Server-Sent Events to push updates to the DOM without requiring polling or manual refreshes.

Instant client and task streaming

The `list_clients` and `list_tasks` tools fetch active recruiting accounts and their associated assignments. When your agent calls these tools, the Vercel AI SDK feeds the JSON arrays directly into your UI components as they arrive. This approach keeps your interface highly responsive. Instead of waiting for a massive payload to resolve, the UI renders client directories and active tasks incrementally as the stream processes.

Track billable hours with this MCP Server

The `list_time_entries` tool retrieves logged hours for job candidates and agency contractors. This MCP Server exposes these records directly to your frontend, allowing your agent to analyze work patterns on the fly. Developers can deploy this serverless-ready connector to run on Edge Functions. You get sub-millisecond start times and direct streaming of time tracking data without maintaining an active Node server.

Setup guide

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

Install `@ai-sdk/mcp` to register the MCP Server tools. Use `createMCPClient` with the Vinkius HTTP endpoint, then pass the tools directly into your generation function.

Yes. The MCP Server transport runs over standard HTTP, making it fully compatible with Vercel's Edge runtime. You can fetch `list_projects` and stream the output without hitting Node.js cold starts.

The SDK catches transport failures at the tool execution level. If a call to `create_task` fails, the error returns as a standard tool result, allowing the model to correct its parameters and retry.

Always call `mcpClient.close()` once your MCP session finishes. This prevents connection leaks and keeps your serverless execution environments clean.

Vinkius runs the server in an isolated V8 sandbox, meaning your raw database credentials never touch the client browser. All requests to `list_clients` and `list_time_entries` are signed with an ephemeral token that expires automatically after the session ends.

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