How to Use the Mews MCP in Mastra AI

Build complex hotel workflows in Mastra AI with conditional branching and automated retries for Mews operations.

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 Mastra AI

Create your Vinkius account to connect Mews to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agentic booking workflows in Mastra AI

Create multi-step processes that check room blocks and availability automatically. Your agent uses `list_room_blocks` and `list_rates` to find the best options before confirming a reservation. If the first attempt fails due to availability, the workflow logic triggers a search for alternative room types. It keeps going until it finds a valid match or alerts your team.

Automated guest communication loops

Task your agent with monitoring guest arrivals using `get_reservations`. It can automatically trigger a confirmation flow or flag missing information in a profile found via `get_guest`. This removes the manual burden of checking guest details before they arrive. The agent handles the back-and-forth and updates the system record if a guest provides updated contact info.

Resilient Mews error handling

Configure your agents to manage API failures with built-in retry logic. When the connection to Mews drops, the workflow waits and attempts the call again without interrupting the operation. This ensures that critical tasks like billing or room assignment finish even if the network blips. Your agents stay on task until the job is done.

Setup guide

Set up Mews MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Mews tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "mews-mcp-client",
  servers: {
    "mews-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Mews Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Mews tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Mews transactions"
);
console.log(result.text);

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 Mastra AI

You add the Mews server to your Mastra agent definition. Once connected, your agents can call tools like `list_services` or `get_reservation` as part of their logic flow.

Absolutely. You write custom workflows that chain tool calls together. For example, check room availability, then get guest details, then create a booking, all in one sequence.

Mastra handles the failure based on your configuration. You can define retries with backoff or use conditional branches to handle the error, such as notifying an admin.

You are subject to the rate limits of your Mews instance. The MCP server ensures that calls are formatted correctly, but your workflow design determines the frequency.

The server uses a zero-trust model. Only the specific agent instance you authorize can access guest profiles, and all traffic stays within the encrypted Vinkius sandbox.

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