How to Use the InflatableOffice MCP in Vercel AI SDK

Q: How do I stream InflatableOffice inventory updates using the Vercel AI SDK?

Install @ai-sdk/mcp and call mcpClient.tools() to grab the listrentalinventory tool. Pass it to streamText to let your agent output live stock counts directly into your React or Next.js components.

Q: Can my Vercel AI SDK app create leads in InflatableOffice without page refreshes?

Yes. The createnewlead tool executes directly inside your Edge Functions, allowing your streaming UI to write new customer inquiries to the database while the user is still typing.

Q: How do I close the MCP connection once my streaming session finishes?

Always call mcpClient.close() at the end of your session block to prevent dangling HTTP connections and avoid hitting API rate limits on your server.

Q: How does the Vercel AI SDK handle the privacy of my customer contact data?

All customer records pulled via listcustomers are processed inside Vinkius's isolated sandbox. No customer names, phone numbers, or addresses are stored or shared with external LLM providers during the streaming process.

Build live party rental booking UIs where your Vercel AI SDK client streams real-time inventory and lead updates directly to the screen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect InflatableOffice MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live rental stock status to Vercel AI SDK UIs

The `list_rental_inventory` tool feeds your real-time rental inventory data directly into your frontend application. Your Vercel AI SDK client calls this tool to check which bounce houses or tents are available, dumping the raw availability data straight into the UI without making users wait for a full page reload. Instead of showing a generic loading spinner, the interface displays live item quantities as they stream from the server. This direct data pipe prevents double-bookings during peak seasonal rushes because the client gets instant inventory answers.

Convert site visitors using this MCP Server lead tool

The `create_new_lead` tool registers incoming rental inquiries directly from your interactive chat interface. When a user describes their event date and desired setup in the chat box, your Vercel AI SDK client instantly pushes those details into your booking pipeline. You do not need background jobs or separate API routes to handle the handoff. The tool handles the schema validation on the fly, meaning your customer sees a confirmation message the second the lead hits your database.

Live event schedule lookups

The `list_scheduled_events` tool exposes your delivery calendar to the streaming interface. Your Vercel AI SDK client reads the scheduled dates to tell customers if their preferred delivery window is already packed with other party setups. This means your UI can proactively suggest alternative setup times during the chat. Your streaming MCP setup gives customers immediate answers about delivery logistics without your office staff picking up a single phone call.

Setup guide

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

Install `@ai-sdk/mcp` and call `mcpClient.tools()` to grab the `list_rental_inventory` tool. Pass it to `streamText` to let your agent output live stock counts directly into your React or Next.js components.

Yes. The `create_new_lead` tool executes directly inside your Edge Functions, allowing your streaming UI to write new customer inquiries to the database while the user is still typing.

Yes. You can manage access tokens dynamically by passing your credentials through the client's built-in authentication provider when initializing the HTTP transport.

Always call `mcpClient.close()` at the end of your session block to prevent dangling HTTP connections and avoid hitting API rate limits on your server.

All customer records pulled via `list_customers` are processed inside Vinkius's isolated sandbox. No customer names, phone numbers, or addresses are stored or shared with external LLM providers during the streaming process.

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