How to Use the AfterShip MCP in Vercel AI SDK

Q: How do I render AfterShip tracking details using the Vercel AI SDK?

Use the gettracking tool within your streamText call. The raw JSON output from the MCP Server streams directly to your React components, letting you render custom UI blocks for each delivery checkpoint.

Q: How does Vercel AI SDK handle invalid tracking numbers with AfterShip?

Your agent will call the detectcourier tool first. If the number is invalid, the MCP Server returns an empty list of couriers, allowing your React UI to prompt the user for a correction immediately.

Q: Do I need to manually close the MCP client connection?

Yes. Always call mcpClient.close() when your streaming session ends. This prevents connection leaks in your Next.js serverless functions.

Get real-time package tracking updates streaming directly into your React components 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 AfterShip MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live package tracking inside Vercel AI SDK

This MCP Server exposes the `get_tracking` and `list_trackings` tools to fetch active shipment statuses instantly. Your AI client calls these tools to grab the current shipping status and pushes the raw JSON payload straight to your frontend stream, bypassing slow database lookups. Because the Vercel AI SDK handles streaming data natively, your users watch the shipping progress update live on screen. There are no loading spinners or blank screens while your React components render the courier checkpoints.

Auto-detecting couriers on the edge

The `detect_courier` tool allows your application to identify shipping carriers from raw tracking numbers. If a user pastes a tracking code without selecting a carrier, your agent passes it to this tool to get a ranked list of likely companies. Running this MCP Server on Vercel Edge Functions means this detection happens with minimal latency. Your edge-rendered UI immediately displays the correct carrier logo and tracking details without round-trips to a central server.

Manage active shipments via AI client

The `create_tracking` and `delete_tracking` tools let your agent manage your active shipping list. When a customer inputs an order number, the agent triggers these tools to register the package or remove old deliveries from the dashboard. Using this MCP Server ensures you don't write custom API wrappers for every shipping courier. The Vercel AI SDK translates user intent into clean tool calls, updating your AfterShip account behind the scenes.

Setup guide

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

Use the `get_tracking` tool within your `streamText` call. The raw JSON output from the MCP Server streams directly to your React components, letting you render custom UI blocks for each delivery checkpoint.

Yes. This MCP integration is fully compatible with Edge runtimes. You can initialize the client inside your API routes without worrying about heavy node-specific dependencies slowing down your edge boots.

Your agent will call the `detect_courier` tool first. If the number is invalid, the MCP Server returns an empty list of couriers, allowing your React UI to prompt the user for a correction immediately.

Yes. Always call `mcpClient.close()` when your streaming session ends. This prevents connection leaks in your Next.js serverless functions.

Yes. The MCP Server processes tracking numbers, customer emails, and SMS phone numbers inside an isolated V8 sandbox. Your sensitive customer details never persist on Vinkius servers, maintaining strict end-to-end data privacy.

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