How to Use the Axle MCP in Vercel AI SDK

Q: How do I connect Axle to Vercel AI SDK?

Install @ai-sdk/mcp and configure createMCPClient with your Vinkius HTTP endpoint. Pass the resulting tools directly into your streamText call.

Q: Can Vercel AI SDK stream Axle location data to React?

Yes. When the agent calls getvehiclelocation, the coordinates stream into your UI components as they arrive. You build the map marker update logic around the tool result payload.

Q: What happens if an Axle load update fails in Vercel AI SDK?

The SDK catches the error from updateload and returns it in the tool execution result. Your frontend can display a toast notification prompting the user to try the shipment update again.

Q: Do I need to manually map driver profiles?

No. The getdriver tool returns the structured profile schema automatically. The MCP protocol maps the fields so your agent reads the output and formats the details for the user.

Build live fleet tracking dashboards with Vercel AI SDK using real-time logistics data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axle MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live fleet data via MCP Server

The `get_vehicle_location` and `get_load` tools feed real-time coordinates and shipment details directly into your frontend components. Your React application renders truck movements as the Vercel AI SDK streams the tool execution results back to the user. Waiting for heavy logistics queries kills user retention. Passing `list_loads` through `streamText` means dispatchers watch the active shipment board populate row by row instantly.

Render HOS limits instantly

Calling `get_driver_availability` checks exact remaining hours of service before assigning a new route. The agent evaluates the time against the destination and prevents illegal dispatch commands. Updating shift states happens through `update_driver_status` right from the chat interface. Dispatchers type a command, the agent confirms the status change, and the UI reflects the new duty cycle immediately.

Surface shipping paperwork

Fetching scanned bills of lading requires the `list_documents` tool to pull associated files for any given shipment. Your users ask for delivery proof, and the agent grabs the exact PDF reference. Building this into a Next.js app doesn't take long. You initialize the client with `createMCPClient`, pass the auth token, and let the agent handle the specific document matching logic.

Setup guide

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

Install `@ai-sdk/mcp` and configure `createMCPClient` with your Vinkius HTTP endpoint. Pass the resulting tools directly into your `streamText` call.

Yes. When the agent calls `get_vehicle_location`, the coordinates stream into your UI components as they arrive. You build the map marker update logic around the tool result payload.

The SDK catches the error from `update_load` and returns it in the tool execution result. Your frontend can display a toast notification prompting the user to try the shipment update again.

No. The `get_driver` tool returns the structured profile schema automatically. The MCP protocol maps the fields so your agent reads the output and formats the details for the user.

Fleet GPS coordinates and HOS records stay secure. Vinkius runs the server in an isolated V8 sandbox, meaning your Vercel AI SDK queries only access the specific vehicle data requested, and the ephemeral container destroys itself after the run.

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