How to Use the MotionTools MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to MotionTools?

Install @ai-sdk/mcp. Run createMCPClient with your Vinkius HTTP endpoint URL. Pass the resulting tools into your streamText function to start rendering logistics data.

Q: Can the Vercel AI SDK stream MotionTools fleet updates directly to React?

Yes. When the agent calls listvehicles, the data streams back to your frontend in chunks. Your React components update the fleet map while the response is still generating.

Q: Does the Vercel AI SDK support creating new MotionTools bookings?

It handles writes without issue. Your agent calls createbooking with the customer details. Once the MCP server confirms the creation, the SDK streams the new booking ID back to your UI.

Build live logistics dashboards. Stream MotionTools data directly into your React frontend 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 MotionTools MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream bookings via Vercel AI SDK

Calling `list_bookings` from your Next.js app means you need real-time logistics data, not loading spinners. When a user asks where their delivery is, the Vercel AI SDK hits `get_booking` and streams the coordinates straight to the UI. The frontend renders the map marker while your agent is still parsing the rest of the payload. You avoid writing custom polling logic. The MCP integration handles the connection to Vinkius, pulling active loads and instantly updating your React components. Users watch their delivery grid populate live without refreshing the page.

Live fleet tracking without the lag

Running `list_drivers` usually requires building a heavy middleware layer. Now your AI client just calls `list_drivers` and `list_vehicles` in parallel. The raw JSON streams back, and your UI components catch the chunks to draw the fleet on the map instantly. If a dispatcher needs to check a specific truck, the agent runs `get_vehicle`. The Vercel AI SDK streams the payload right into a side panel. You get the VIN, capacity, and current driver assignment rendered before the user even finishes typing their query.

Dynamic territory lookups

Delivery zones change constantly, so hardcoding them is a mistake. Using `list_service_areas`, your agent queries this MCP Server and streams the active polygons to your frontend map. The customer types their address, and the UI immediately shows if they fall inside a valid zone. When a new customer signs up, the agent cross-references their location with `get_service_area`. If they fit, it triggers `create_booking` on the spot. The Vercel AI SDK ensures the user sees the confirmation UI update the exact millisecond the endpoint returns success.

Setup guide

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

Install `@ai-sdk/mcp`. Run `createMCPClient` with your Vinkius HTTP endpoint URL. Pass the resulting tools into your `streamText` function to start rendering logistics data.

Yes. When the agent calls `list_vehicles`, the data streams back to your frontend in chunks. Your React components update the fleet map while the response is still generating.

It handles writes without issue. Your agent calls `create_booking` with the customer details. Once the MCP server confirms the creation, the SDK streams the new booking ID back to your UI.

Vinkius handles the underlying OAuth and API keys. You just pass your single Vinkius endpoint token into the transport configuration when setting up the client.

Your logistics data stays protected. When your agent pulls names and addresses via `list_customers`, the request runs inside a V8 Isolate Sandbox. The environment is ephemeral and tears down immediately after the query finishes, leaving zero trace of your customer records.

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