Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Quest Apartment Hotels MCP Server Find a Quest in Sydney with a gym for 3 nights next week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for Quest Apartment Hotels, enabling AI assistants (ChatGPT, Claude, Gemini) to search properties, check availability, compare rates, and make bookings across Quest's Australian portfolio.
POC Note: Availability and rates are simulated with deterministic fake data. Bookings are stored in-memory and reset on each cold start.
Tool | Description |
| Find properties by city, state, or amenity |
| Full details for a specific property |
| Availability for a property and date range |
| Rate plans for a property and stay |
| Combined search + availability in one call |
| Price estimate without creating a booking |
| Make a reservation |
| Look up an existing booking by confirmation number |
Related MCP server: Hostaway MCP Server
Quest-MCP/
├── api/
│ └── mcp.ts # All server logic (single file)
├── package.json
├── tsconfig.json
├── vercel.json # Routes /mcp → /api/mcp
└── .gitignoreNode.js 20+
Vercel CLI (installed as a dev dependency)
# Clone the repo
git clone https://github.com/YOUR_USERNAME/Quest-MCP.git
cd Quest-MCP
# Install dependencies
npm install
# Type-check (no output = success)
npm run build
# Start local dev server
npm run devThe server will be available at http://localhost:3000/mcp.
npx @modelcontextprotocol/inspectorSet the URL to http://localhost:3000/mcp and transport to Streamable HTTP.
The project is configured to auto-deploy to Vercel on every push to main.
Push this repo to GitHub
Go to vercel.com → Add New Project → Import your GitHub repo
Vercel will auto-detect the project — no extra config needed
Click Deploy
After the first deploy, every git push to main triggers a new deployment automatically.
Your MCP endpoint will be at:
https://YOUR-PROJECT.vercel.app/mcpNone required for this POC. All data is hardcoded.
Per the OpenAI MCP testing instructions:
Open chatgpt.com and start a new conversation
Click the Tools (plug) icon → Add a tool → MCP Server
Enter your Vercel URL:
https://YOUR-PROJECT.vercel.app/mcpSet approval to No approval required (for testing)
Click Connect
ChatGPT will discover all 8 tools automatically. Try prompts like:
"Find me a Quest hotel in Melbourne for 3 nights from next Friday"
"What Quest properties in Sydney have a gym?"
"Check availability at Quest Docklands for 15–18 March 2025 and give me the best rate"
"Book a studio at Quest on William for 2 nights from March 20, name John Smith"
The server includes 27 real Quest Australia properties across:
State | Count |
VIC | 7 |
NSW | 6 |
QLD | 4 |
ACT | 2 |
WA | 3 |
SA | 1 |
NT | 1 |
TAS | 1 |
Regional | 2 |
Code | Description | Adjustment |
FLEX | Flexible rate | +10% |
STD | Standard rate | base |
ADVP | Advance purchase (7d+) | −10% |
CORP | Corporate rate | −15% |
LONG7 | Weekly rate (7+ nights) | −15% |
Weekend surcharge: +20% on Fri/Sat/Sun nights.
Transport: Streamable HTTP (stateless — required for Vercel serverless)
Sessions: Disabled (sessionIdGenerator: undefined) — each request is independent
CORS: Open (*) — required for browser-based AI clients
Availability: Deterministic hash on propertyId|date|roomType → 75% available
Bookings: In-memory Record<string, Booking> — resets on cold start
For a production implementation, replace the in-memory store with a database and connect to Quest's RMS API.
This server cannot be deployed
Book real hotel and resort stays from any AI agent: all-in pricing, hosted Stripe checkout, no key.
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
Vacation rental discovery, direct booking, and property protection for AI agents.
Real-time Booking.com rates for agents. Three things people do with this server. Scan for rate gaps: price_as_seen_from prices the same room from another market, so an agent can sample a property across countries and compare. Put live search in your app: search a destination or look a property up by name, no internal IDs, room-level rates as flat JSON. Run a 24/7 AI travel agent: add the server, sign in with Google, and schedule it. No ads, no sponsored content. You bring your own RapidAPI key, so every search is billed to your plan and never to anyone else's. Add https://hotels.flightpowers.com/mcp , click Sign in, sign in with Google, and paste your RapidAPI key once on the page that opens. Scripts and clients without a sign-in button send the key as x-rapidapi-key on the same URL.
