How to Use the Mews MCP in Vercel AI SDK

Q: How are guest payments handled?

You use listpayments to fetch the transaction history. The server returns the settlement status, which your code then displays in the interface.

Stream real-time Mews property data directly into your Vercel AI SDK frontends for live guest and reservation updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mews MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live reservation streaming with AI SDK

Feed live reservation queues into your UI without waiting for background jobs to finish. Your app calls `get_reservations` to pipe incoming arrivals straight to your dashboard components. Everything renders as the data arrives. Guests see their status shift from pending to active the moment the back-end confirms the booking.

Instant guest profile retrieval

Surface complete guest history by querying `search_guests` during a chat session. Your agent pulls nationality, loyalty status, and past stay preferences into the context window instantly. Stop digging through manual tabs. The AI reads the profile and answers specific questions about past visits or dietary requests while the user types.

Automated financial transparency

Expose invoice details to your users by connecting `list_bills` and `list_payments` to your frontend state. Your application renders live billing summaries and payment statuses without manual refreshes. This keeps the guest informed about their current balance. It also reduces the number of front-desk inquiries regarding pending charges or past transactions.

Setup guide

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

You instantiate the MCP client and pass the tools directly into your `streamText` configuration. It handles the connection to your Mews instance, letting you call functions like `get_reservation` from inside your React components.

Yes. Because the SDK is built for streaming, it processes the tool output from the Mews MCP server as it arrives. Your frontend updates the DOM immediately.

The Mews server acts as the bridge. You connect your AI client to the Vinkius endpoint, and the tools translate your natural language requests into the correct API calls.

You use `list_payments` to fetch the transaction history. The server returns the settlement status, which your code then displays in the interface.

Vinkius runs the Mews server in a sandboxed isolate. Your API keys never leave the secure environment, and all requests are scoped only to the data types defined in the Mews toolset.

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