How to Use the Craftboxx MCP in Vercel AI SDK

Q: How do I handle Craftboxx authentication in the Vercel AI SDK?

You pass your endpoint token via the createMCPClient transport configuration when setting up the Vercel AI SDK. Vinkius manages the underlying OAuth handshake so your frontend code never exposes raw API keys. This keeps your Edge Functions secure and simple.

Q: Can I stream Craftboxx order details to a React component using the Vercel AI SDK?

Yes, the Vercel AI SDK uses streamText to pipe tool outputs from getorderdetails directly into your UI. Your React components render the data chunks as the MCP server returns them. This eliminates the need for manual API polling.

Q: How do I close the MCP connection after fetching Craftboxx customer lists?

You must invoke mcpClient.close() once your agent finishes executing the listcustomers tool. Leaving connections open inside serverless functions will exhaust your Vercel AI SDK execution limits. Always clean up resources in your final block.

Stream real-time Craftboxx field schedules and order updates directly into your React UI with 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 Craftboxx MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Craftboxx schedules using Vercel AI SDK

The `list_appointments` tool lets your Vercel AI SDK agent fetch field work schedules and push them directly to your frontend. Instead of waiting for a full API roundtrip, this integration streams active technician schedules straight into your user interface components. Your users watch the schedule populate in real-time as the agent queries Craftboxx. By skipping the standard loading spinner, this MCP server setup keeps your Next.js dashboard feeling incredibly fast and responsive.

Instant Craftboxx order creation on the Edge

The `create_order` tool handles the immediate generation of new craft orders directly from your streaming chat interface. Running your Vercel AI SDK application on Edge Functions means your agent processes order details and triggers the Craftboxx API with minimal latency. You get immediate UI feedback as the agent confirms the new order ID. The agent can immediately follow up by calling `list_tasks` to show the newly generated task list to the user without blocking the main thread.

Real-time business metrics without UI lag

The `get_business_stats` tool pulls high-level performance data from your Craftboxx account to display on developer-built dashboards. When paired with Vercel AI SDK helper functions, the retrieved statistics render instantly as the AI agent structures the raw numbers. This setup avoids the typical delay of server-side data fetching by rendering metrics as they stream. Your agent can instantly compare these stats with resource availability by querying `list_vehicles_resources` in the same execution block.

Setup guide

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

You pass your endpoint token via the `createMCPClient` transport configuration when setting up the Vercel AI SDK. Vinkius manages the underlying OAuth handshake so your frontend code never exposes raw API keys. This keeps your Edge Functions secure and simple.

Yes, the Vercel AI SDK uses `streamText` to pipe tool outputs from `get_order_details` directly into your UI. Your React components render the data chunks as the MCP server returns them. This eliminates the need for manual API polling.

The SDK handles parallel tool execution, allowing your agent to run `list_materials` alongside other lookup tools simultaneously. It aggregates the inventory list and streams the formatted table to your users in one motion. This speeds up material checks during active client chats.

You must invoke `mcpClient.close()` once your agent finishes executing the `list_customers` tool. Leaving connections open inside serverless functions will exhaust your Vercel AI SDK execution limits. Always clean up resources in your final block.

Your customer records and financial statistics remain inside the Vinkius V8 Isolate sandbox during execution. This zero-trust environment destroys all temporary data the moment your Vercel AI SDK session terminates. No sensitive operational data ever persists on our servers.

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