How to Use the Giddyup MCP in Vercel AI SDK

Q: How do I connect the Giddyup MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and initialize with createMCPClient. Point the HTTP transport URL to your Vinkius endpoint. Then pass mcpClient.tools() into your streamText function.

Q: Can Vercel AI SDK stream Giddyup invoices to the frontend?

Yes. When the model invokes listinvoices, the raw JSON streams straight to your UI components. You render the billing table as the data arrives.

Q: What happens if a job update fails during a stream?

The tool call for updatejob returns an error object to the AI. You can configure your React error boundaries to catch this and prompt the user to try again.

Q: Does this MCP Server expose customer billing data?

The server accesses financial records via listinvoices. Vinkius runs the connection inside a zero-trust V8 Isolate sandbox. The data routes directly to your AI client and is destroyed immediately after the session ends.

Build live field service dashboards. Stream Giddyup dispatch data directly to your frontend 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 Giddyup MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Giddyup dispatch boards to the UI

Your Next.js app needs to show active field technicians. Instead of polling an API and displaying loading spinners, your AI client fetches data via `list_jobs` and streams the JSON directly into your React components. The dispatcher sees trucks moving on the map instantly. When a customer calls in, the agent uses `get_job` to pull the current status. If the route changes, `update_job` fires. The entire interaction happens live in the browser, making your interface feel incredibly fast.

Interactive lead capture in Vercel AI SDK

You do not want static forms for construction quotes. Build a conversational interface where the user types what they need built. The agent queries `get_customer` to see if they exist in your system. If they are new, the model calls `create_lead` with their project details. Vercel streams the confirmation back to the user interface as the record hits the database. No waiting around for a page reload.

Real-time mobile workforce visibility

Field ops run on tight schedules. You can hook up `list_users` to pull the active roster of technicians. The AI evaluates who is closest to an emergency call before making a routing decision. Before dispatching, the system pings `check_giddyup_status` to ensure the mobile routing engine is online. You build this entirely with Edge functions, keeping the latency low and the frontend responsive while this MCP Server handles the heavy lifting.

Setup guide

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

Install `@ai-sdk/mcp` and initialize with `createMCPClient`. Point the HTTP transport URL to your Vinkius endpoint. Then pass `mcpClient.tools()` into your `streamText` function.

Yes. When the model invokes `list_invoices`, the raw JSON streams straight to your UI components. You render the billing table as the data arrives.

Vinkius handles the underlying API credentials. You just provide your single endpoint token in the setup. Add it to your environment variables and you are set.

The tool call for `update_job` returns an error object to the AI. You can configure your React error boundaries to catch this and prompt the user to try again.

The server accesses financial records via `list_invoices`. Vinkius runs the connection inside a zero-trust V8 Isolate sandbox. The data routes directly to your AI client and is destroyed immediately 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