How to Use the Navisphere MCP in Vercel AI SDK

Q: What's the best way to handle bidding on Navisphere freight in a Vercel AI SDK app?

Use the submitbid tool. Your UI can collect the bid amount, then your AI client invokes the tool. The streaming response gives you immediate feedback on whether the bid was accepted.

Q: Can I get rate estimates before bidding?

Yes. The getrateestimate tool lets you check the expected cost for a shipment. You can call this before using submitbid to make sure your offers are competitive.

Build live logistics dashboards with the Vercel AI SDK. Stream freight data from Navisphere directly into your Next.js or Svelte UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Navisphere MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find and Bid on Freight in Real-Time

Use the `search_available_loads` tool to pull freight listings straight from Navisphere. As the data streams in, your UI updates instantly, showing users new loads without a page refresh. It's fast enough for live load boards. Once a user spots a good load, they can get more info with `get_load_details` and then fire off a bid using the `submit_bid` tool. Your frontend gets confirmation back just as quickly. No spinners, just action.

Stream Live Shipment Tracking Data

The `track_shipment` tool gives you a live feed of a shipment's location and status. With the Vercel AI SDK, you can pipe these updates directly into a map component in your React app. Your customers see the truck move in real time. For more detailed histories, you can pull a full log with `get_tracking_events`. This lets you build out complete shipment timelines, showing every pickup, departure, and arrival event as it happens.

Manage Shipments with this MCP Server

Go beyond just tracking. This MCP server lets you create new shipments with `create_shipment` and accept offers using `accept_offer`. Your app becomes a command center, not just a viewer. You can also manage compliance by uploading proof of delivery or other documents with `upload_shipment_documents`. It's all handled through the same simple interface your AI client uses.

Setup guide

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

You connect them using an MCP endpoint token from Vinkius. Install the `@ai-sdk/mcp` package, use `createMCPClient` with your URL, and pass the tools from `mcpClient.tools()` into your `streamText` call. It's just a few lines of code.

Yes, that's exactly what this is for. The Vercel AI SDK streams results from the `search_available_loads` tool, so your UI can display new freight opportunities the moment they're found. No polling, no waiting.

Use the `submit_bid` tool. Your UI can collect the bid amount, then your AI client invokes the tool. The streaming response gives you immediate feedback on whether the bid was accepted.

Yes. The `get_rate_estimate` tool lets you check the expected cost for a shipment. You can call this before using `submit_bid` to make sure your offers are competitive.

Your load details and bid information are processed in an ephemeral, sandboxed environment on Vinkius. All communication is over HTTPS, and your specific endpoint token authenticates every request. The server itself doesn't store your data long-term.

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