How to Use the Flexport MCP in Vercel AI SDK

Q: What is the best way to handle large shipment lists?

Use pagination parameters within the listshipments tool call. This keeps the streamed payload small and ensures your React components render the initial cargo lists quickly without hitting Edge function execution limits.

Build live-updating logistics dashboards with Vercel AI SDK streaming Flexport shipping data straight to your React frontends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flexport MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live freight updates via Vercel AI SDK

Stop making users stare at loading spinners. This Flexport MCP Server lets your AI client fetch active cargo locations using `list_shipments` and stream the status changes directly to your Next.js UI as they happen. When a user asks where their container is, the SDK handles the data stream on the Edge. It calls `get_shipment` to pull coordinates and ETAs, rendering the map points in real-time without blocking the main browser thread.

Instant document rendering in your web apps

Handling customs paperwork is usually a slow, multi-step headache. With this integration, your web app lets users request import files, prompting the agent to fetch metadata via `get_document` and provide a direct download URL. The Vercel AI SDK pipes the URL from `download_document` straight into your custom UI component. Your users get immediate access to their bills of lading and commercial invoices without waiting for a full page reload.

Interactive billing components built on edge functions

Keep your finance team in their workflow by rendering live invoice data in your application. Your agent uses `list_shipment_invoices` to pull outstanding balances and displays them inside interactive React components. Using the SDK's tool-calling capabilities, the agent can drill down into specific billing items with `get_invoice`. It renders payment breakdowns on the fly, making invoice reconciliation fast and interactive.

Setup guide

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

You should implement caching at the Edge Route Handler level. Since this MCP Server runs in a secure sandbox, your Vercel AI SDK can safely cache responses from tools like `list_shipments` to prevent hitting Flexport API thresholds during high-traffic sessions.

Yes, you can stream document metadata directly to your UI. Use `list_documents` within your SDK tool configuration to let the agent retrieve file lists, then stream the output to custom React components that render download buttons using `download_document`.

Store your Flexport API credentials as environment variables in your Vercel project dashboard. When initializing the MCP client, inject these variables into the transport configuration to keep your secrets hidden from the client-side bundle.

Use pagination parameters within the `list_shipments` tool call. This keeps the streamed payload small and ensures your React components render the initial cargo lists quickly without hitting Edge function execution limits.

Vinkius runs this MCP Server in an isolated V8 sandbox, ensuring your commercial invoices and PO details are never exposed. When your agent calls `get_purchase_order` or `get_invoice`, the data travels through encrypted channels directly to your Vercel deployment, bypassing public logging.

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