How to Use the HCSS MCP in Vercel AI SDK

Q: How do I stream HCSS telematics data using the Vercel AI SDK?

Use the getequipmentmeters tool within your streaming text or object generator via this MCP connection. Set up the Vercel AI SDK transport to pipe the telemetry payload directly to your React components, avoiding stale UI states.

Q: Can the Vercel AI SDK handle real-time HCSS cost code lookups?

Yes, the SDK calls listcostcodes at the edge to match active field operations with your budget codes. This setup feeds instant financial data straight into your frontend without blocking the main browser thread.

Q: How do I configure this HCSS MCP Server with Vercel AI SDK edge functions?

Initialize the client using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the tools directly into streamText to let your agent call HCSS endpoints within the 25-second Vercel execution limit.

Feed real-time heavy construction telematics and field timecards directly into your React frontends 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 HCSS MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream HCSS GPS coordinates directly to your UI

`get_equipment_location` pulls raw GPS coordinates for any heavy asset in your fleet and pipes them straight to your Vercel AI SDK frontend via our high-speed MCP bridge. Your users watch equipment move on the map in real-time without hitting refresh or waiting on API polling loops. We built this to bypass standard loading spinners by streaming the location payload directly into your edge-rendered UI. It binds the telematics stream to your map components so field managers see immediate asset updates.

Render bidding estimates live during client chats

`list_estimates` fetches raw HeavyBid data to display active project bids while your AI agent discusses numbers with clients. Instead of dumping a wall of text, the Vercel AI SDK streams structured bid items into custom React components as the model generates them. Your frontend renders clean tables containing unit prices and quantities from `get_bid_items` the millisecond the model resolves the tool call. This eliminates the lag between model execution and UI updates during critical budget reviews.

Build live timecard audits with this MCP Server

`list_timecards` pulls active labor hours from HeavyJob to let your Vercel AI SDK application run instant, user-facing compliance checks. The tool exposes raw hours, cost codes, and employee IDs directly to your streaming interface. By combining this with `list_employees`, your edge function cross-references field hours against active rosters on the fly. The user watches the validation results populate line-by-line as the LLM processes the payroll data.

Setup guide

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

Use the `get_equipment_meters` tool within your streaming text or object generator via this MCP connection. Set up the Vercel AI SDK transport to pipe the telemetry payload directly to your React components, avoiding stale UI states.

Yes, the SDK calls `list_cost_codes` at the edge to match active field operations with your budget codes. This setup feeds instant financial data straight into your frontend without blocking the main browser thread.

Initialize the client using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the tools directly into `streamText` to let your agent call HCSS endpoints within the 25-second Vercel execution limit.

The client handles timeouts gracefully by streaming partial payloads. If `list_equipment` experiences latency, the SDK passes the available cached fleet data to the UI so your users never stare at a frozen screen.

Vinkius isolates every session inside a secure, ephemeral V8 sandbox to prevent data leaks. Your raw GPS coordinates and payroll hours are never saved to disk or used for training models, keeping your field operations 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