How to Use the Apaleo MCP in Vercel AI SDK

Q: How do I initialize the Apaleo MCP Server with the Vercel AI SDK?

Install @ai-sdk/mcp and ai via npm, then call createMCPClient pointing to your Vinkius endpoint URL. You pass mcpClient.tools() directly into the tools parameter of streamText and remember to call mcpClient.close() when the session ends.

Q: How does the Vercel AI SDK handle Apaleo rate plans?

The SDK calls listrateplans to fetch pricing structures directly from the PMS. It then streams these options directly into your custom UI, allowing users to compare room rates live.

Q: Do I need to manage OAuth tokens for Apaleo manually?

No, you configure the authProvider during the createMCPClient setup. Vinkius handles the underlying token exchange so your frontend client can focus entirely on rendering the data.

Q: Is guest billing data safe when using this MCP Server?

Yes, guest folios and invoice data fetched via listfolios never persist on Vinkius. Every transaction runs inside an ephemeral, zero-trust V8 isolate sandbox that encrypts all PMS payloads in transit.

Render real-time Apaleo reservation updates and room availability directly in your React components 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 Apaleo MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Room Availability Feeds via Vercel AI SDK

The `check_availability` tool exposes real-time room counts per room type per day directly to your frontend application. When your user asks for open dates, this MCP Server fetches the data from Apaleo and streams it immediately to the UI without blocking the page render. By coupling this tool with `list_room_types`, your Vercel AI SDK client renders custom UI cards for Deluxe or Suite rooms as the data arrives. You don't make the user stare at a spinning loader while fetching inventory.

Instant Guest Billing with Streaming Folios

The `list_folios` tool retrieves detailed guest billing records linked to specific hotel reservations. Your Vercel AI SDK setup feeds this raw ledger data straight into the edge runtime, letting your agent format itemized receipts on the fly. Because `list_invoices` works alongside this, you can build a self-service checkout UI. The client streams the structured invoice lines directly into a clean React table layout before the connection closes.

Conversational Front-Desk Dashboard

The `list_reservations` tool exposes the active front-desk queue to your web-based management interface. This MCP Server allows your React-based agent to pull up guest check-in schedules using simple natural language queries. Your app combines this with `get_reservation` to display specific booking details instantly. The Vercel AI SDK handles the asynchronous data stream, updating the receptionist's screen as soon as the PMS returns the payload.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` via npm, then call `createMCPClient` pointing to your Vinkius endpoint URL. You pass `mcpClient.tools()` directly into the `tools` parameter of `streamText` and remember to call `mcpClient.close()` when the session ends.

Yes, the server streams raw booking JSON via the SDK's edge-compatible runtime. Your agent triggers `get_reservation` and pipes the structured property data directly into your React UI components without delay.

The SDK calls `list_rate_plans` to fetch pricing structures directly from the PMS. It then streams these options directly into your custom UI, allowing users to compare room rates live.

No, you configure the `authProvider` during the `createMCPClient` setup. Vinkius handles the underlying token exchange so your frontend client can focus entirely on rendering the data.

Yes, guest folios and invoice data fetched via `list_folios` never persist on Vinkius. Every transaction runs inside an ephemeral, zero-trust V8 isolate sandbox that encrypts all PMS payloads in transit.

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