How to Use the GoBolt MCP in Vercel AI SDK

Q: How do I stream GoBolt rates in Next.js using the Vercel AI SDK?

You initialize the client with createMCPClient using your Vinkius MCP endpoint. Pass the tools directly to streamText and let the SDK handle the live UI rendering.

Q: Can the Vercel AI SDK handle bulk order creation with GoBolt?

Yes, your agent can call createshippingorder repeatedly inside a loop. The SDK streams the progress of each created shipment back to your dashboard in real-time.

Q: How does the Vercel AI SDK select carrier speeds with GoBolt?

The agent evaluates the active cart and invokes findfastestrate or findcheapestrate based on user preferences. It then streams the chosen carrier choice directly into your UI components.

Q: What happens if the GoBolt API goes offline?

Your application can run verifyapiconnection to check downstream carrier health. If the check fails, the SDK lets you fall back to a static shipping rate gracefully.

Get real-time shipping costs and live tracking directly in your Next.js UI using the Vercel AI SDK to call GoBolt tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoBolt MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time rate streaming with Vercel AI SDK

Your users hate waiting for loading spinners when checking shipping options. By pairing the Vercel AI SDK with this MCP Server, your app streams actual shipping costs directly into your checkout page. The agent runs `get_shipping_rates` in the background and pushes the raw numbers straight to the client-side state without making the user wait for a full page reload. If the buyer wants the absolute lowest price or needs the package tomorrow, the agent fires `find_cheapest_rate` or `find_fastest_rate` on the fly. Because it runs on Vercel Edge Functions, the response returns instantly, letting your interface update dynamically as the options resolve.

Live tracking updates inside the chat UI

Stop building static tracking portals that require manual refreshes. This setup lets your customer support agent pull live delivery statuses and render them inside a clean chat bubble. The agent hits `track_shipment` to grab the current carrier location and displays it immediately. For customers who want the entire delivery timeline, the agent calls `get_tracking_history` to map out every stop. The Vercel AI SDK streams these milestones as they arrive, turning raw logistics data into a clear, step-by-step visual timeline on screen.

Instant label generation and order edits

Warehouse operators need to fix address typos without digging through heavy shipping software. Your support team can just tell the agent to update a package, prompting the MCP Server to run `modify_shipping_order` behind the scenes. Once the address details are corrected, the agent calls `get_shipping_labels` to pull the new printable PDF. The Vercel AI SDK handles the file stream, rendering the shipping label directly in the operator's browser window for instant printing.

Setup guide

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

You initialize the client with `createMCPClient` using your Vinkius MCP endpoint. Pass the tools directly to `streamText` and let the SDK handle the live UI rendering.

Yes, your agent can call `create_shipping_order` repeatedly inside a loop. The SDK streams the progress of each created shipment back to your dashboard in real-time.

The agent evaluates the active cart and invokes `find_fastest_rate` or `find_cheapest_rate` based on user preferences. It then streams the chosen carrier choice directly into your UI components.

Your application can run `verify_api_connection` to check downstream carrier health. If the check fails, the SDK lets you fall back to a static shipping rate gracefully.

All customer names, delivery addresses, and tracking numbers are processed inside Vinkius's isolated sandboxes. The server never stores this data, passing it directly to the carrier APIs and discarding it immediately after the request completes.

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