How to Use the Arrivy MCP in Vercel AI SDK

Q: How do I show a list of Arrivy tasks in my Next.js app with the Vercel AI SDK?

You'll call the listtasks tool through the Vercel AI SDK's streamText or generateText function. Then, you can use the streaming UI helpers to render the list of tasks as the data arrives from the MCP server, creating a live-updating view for your users.

Q: What's the best way to get details for one specific Arrivy task using the Vercel AI SDK?

Use the gettask tool. Pass the task ID from your application to your agent, which then calls the tool. The details for that single task will be returned, which you can then display in your UI.

Q: How do I check if my connection to the Arrivy MCP is working?

Run the getaccountcheck tool. It’s a simple diagnostic tool that confirms your authentication token is valid and the server is responsive. It's good practice to run this once when your application initializes.

Build UIs that show Arrivy field service data in real-time with the Vercel AI SDK. Your users see crew locations and task updates as they happen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arrivy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create and manage jobs from your UI

This toolset lets your user interface directly manipulate your Arrivy account. You can build forms that use `create_customer` to add a new client, then immediately follow up with `create_task` to schedule their job. It's a direct line from your frontend to your field service backend. Updating a job is just as simple. Give your users a way to change details, and your code calls `update_task` with the new information. The change is reflected instantly in Arrivy. There’s no separate backend API to build or maintain.

Stream Arrivy data into React components

Stop showing loading spinners for field service data. With the Vercel AI SDK, you can stream lists of jobs and personnel directly into your app's interface. Your agent calls `list_tasks` or `list_crews`, and the results render on screen as they arrive. This makes for a much better user experience. Instead of a blank screen, your dispatchers or managers see a dashboard that populates live. You can even use `get_task` to stream the details of a single, specific job as it's being updated in the field.

Connect your MCP Server in minutes

Getting your Vercel AI SDK project connected to Arrivy is straightforward. The `get_account_check` tool gives you a simple way to confirm your connection and credentials are valid before you make any other calls. It’s a quick ping to make sure everything is working. This MCP Server exposes all the core Arrivy operations you need. Once you instantiate the client with your Vinkius endpoint, you can get a list of available tools and pass them straight to your text generation function. It’s built to get you from setup to a working prototype quickly.

Setup guide

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

You'll call the `list_tasks` tool through the Vercel AI SDK's `streamText` or `generateText` function. Then, you can use the streaming UI helpers to render the list of tasks as the data arrives from the MCP server, creating a live-updating view for your users.

Yes, absolutely. Your form submission can trigger an AI client call that uses the `create_customer` and `create_task` tools. The data from your form fields becomes the parameters for those tool calls, adding the records directly to Arrivy.

Use the `get_task` tool. Pass the task ID from your application to your agent, which then calls the tool. The details for that single task will be returned, which you can then display in your UI.

Run the `get_account_check` tool. It’s a simple diagnostic tool that confirms your authentication token is valid and the server is responsive. It's good practice to run this once when your application initializes.

Yes. Your connection to the Arrivy MCP Server is encrypted. Vinkius runs each server in an ephemeral, sandboxed environment, meaning your data—like customer names, addresses, and task details—is processed for the request and not stored long-term. Your Vinkius token handles all the authentication securely.

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