How to Use the Beeline MCP in Vercel AI SDK

Build React and Next.js interfaces that stream Beeline workforce data straight to users with 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 Beeline MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Beeline requisitions into Vercel AI SDK.

Calling `search_requisitions` or `list_requisitions` pulls external workforce job postings directly from Beeline VMS into your Next.js frontend. Your users do not sit staring at a loading spinner while the server fetches fifty open roles. Data streams into the UI component the second the Vercel AI SDK receives the chunks. Building dashboards for hiring managers requires speed. You map the `get_requisition` output to React server components, rendering candidate requirements line by line as the agent generates the text. Edge functions handle the Vinkius MCP connection without blocking the main thread.

Render contractor hours instantly.

Fetching contractor hours via `list_timesheets` feeds raw billable data directly to your frontend agent. Instead of making users click through five Beeline menus, they just ask the chat interface for this week's hours. The agent triggers `get_timesheet` and the results populate a custom Vue or React table immediately. Managers need to approve contractor pay fast. Connecting this MCP Server to your UI means you build interactive widgets based on live VMS data. Your agent formats the hours, calculates totals, and displays everything before the user even finishes their coffee.

Build fast vendor management views.

Running `list_suppliers` alongside `list_assignments` gives your Vercel AI SDK application a complete map of who works where. You feed these tool outputs into a generative UI component. The frontend renders active vendor contracts and specific worker placements side-by-side. Tracking external headcount usually involves exporting spreadsheets. Now you pass an authenticated Vinkius token to `createMCPClient`, call the tools, and let the AI stream the exact assignment details into a Svelte dashboard. The user gets answers about contractor spend without touching the VMS backend.

Setup guide

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

Install @ai-sdk/mcp and initialize createMCPClient with your Vinkius HTTP URL. Pass the resulting tools to streamText or generateText. Remember to call mcpClient.close() when the stream finishes.

Yes, the SDK handles the streaming out of the box. You call the timesheet tools, and the data chunks flow straight into your React server components. Users see contractor hours appear incrementally.

Vinkius endpoints work perfectly with edge deployments. You just need to ensure your transport configuration uses the HTTP type. The remote execution happens in our V8 isolates, keeping your edge functions light.

The SDK will stream an error state to your UI. You handle this by rendering a fallback component or prompting the user to retry the specific requisition search. Vinkius manages the underlying connection stability.

Timesheet records, assignment details, and user profiles never touch a persistent disk. Vinkius runs the query inside an ephemeral V8 sandbox that terminates exactly when the request ends. You only pass a single endpoint token to authenticate the zero-trust tunnel.

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