How to Use the BookingLive MCP in Vercel AI SDK

Q: How do I connect the BookingLive MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and ai via npm. Use createMCPClient to point to your Vinkius endpoint, then pass the tools from your client directly into streamText or generateText. Remember to call close() when the session ends to prevent memory leaks.

Q: Can I stream booking updates live using Vercel AI SDK and BookingLive?

Yes. When your agent calls getorderdetails, the Vercel AI SDK streams the JSON payload directly into your UI components. This means your users see reservation changes, pricing updates, and booking statuses render in real-time without hitting loading spinners.

Q: How does BookingLive handle user notifications during an active Vercel AI SDK session?

Your agent can call setordernotification to configure SMS or email preferences during the chat. It can also trigger sendemailtocustomers to dispatch custom confirmation messages immediately after a booking is finalized.

Build real-time booking interfaces where your Vercel AI SDK app streams live reservation data straight to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BookingLive MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream BookingLive MCP Server availability directly to your UI

The `get_product_availability` tool checks real-time booking slots for specific date ranges. When your user asks for open slots, your AI client pulls the raw availability data and streams it directly into your frontend components without making the user wait for a full page reload. You can also fetch specific resource constraints using `get_resource_availability`. This keeps your UI reactive, letting users see which staff or rooms are free as the agent processes the request on the edge.

Build booking orders on the edge

The `start_order` tool initiates a new customer reservation with member details and item selections. Your application takes the user's natural language input and spins up a draft reservation instantly, feeding the structured response straight back to your Vercel AI SDK stream. If the user changes their mind, the agent calls `abort_order` to clean up pending items before they lock up inventory. This direct control over the cart lifecycle prevents stale reservations from blocking actual sales.

Modify active reservations in real-time

The `update_order_param` tool edits specific variables on active bookings based on user prompts. Your UI updates the booking state in real-time as the agent updates the parameters behind the scenes. Once the user confirms the changes, the agent invokes `complete_order` to finalize the transaction. This eliminates the need for multi-step forms, replacing them with a single chat input that manipulates the booking API.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` via npm. Use `createMCPClient` to point to your Vinkius endpoint, then pass the tools from your client directly into `streamText` or `generateText`. Remember to call `close()` when the session ends to prevent memory leaks.

Yes. When your agent calls `get_order_details`, the Vercel AI SDK streams the JSON payload directly into your UI components. This means your users see reservation changes, pricing updates, and booking statuses render in real-time without hitting loading spinners.

Your agent can call `set_order_notification` to configure SMS or email preferences during the chat. It can also trigger `send_email_to_customers` to dispatch custom confirmation messages immediately after a booking is finalized.

It does. The Vinkius hosted MCP server communicates over standard HTTP/SSE protocols, making it compatible with lightweight edge runtimes. You don't have to worry about heavy dependencies slowing down your serverless cold starts.

Your customer emails and order details remain completely secure because Vinkius runs the server in an isolated V8 sandbox. No database credentials or raw reservation payloads are stored on the host, ensuring compliance with standard data protection policies.

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