searchLABSCO SUMMARY
Filters at the level people actually ask about.
Blackout curtains, pet fees, pillow menus, disability-friendly bed height — these are the details that decide a booking and that price-and-location search cannot express. Exposing get_filters as its own tool is the right call, because it lets the model discover valid values rather than inventing them. The payment split is worth noting for anyone building on top: the agent produces a link, the human pays, the booking confirms — the model never touches card data. There is also an affiliate programme paying 4%, 7% or 10% of booking value by monthly volume.
What it is
The official WinWin.travel MCP server: a hosted endpoint giving an agent access to hotel inventory the README puts at 3 Million+ properties, with search, filter discovery, reservation and status tools. Booking completes through a payment link the guest opens themselves, so card details never pass through the model.
What you get
search— available room offers by destination, stay dates and guest composition, with optional filters covering meal plans, cancellation policies, amenities, accessibility features, pet policies and 500+ other criteriaget_filters— the full list of valid filter values, which is what you call before searching to avoid guessingcreate_reservation— books a selected offer and returns a payment link; the booking confirms automatically once payment completesget_reservation_status— checks a booking using the identifiercreate_reservationreturnedechofor connection diagnostics andtest_mcp_authenticationfor confirming the token is valid- An n8n workflow template for a Telegram travel-agent bot, shipped as a demo rather than a production architecture
Requirements
An access token, sent as an Authorization: Bearer header. Nothing runs locally — clients that support remote MCP servers point straight at https://mcp.winwin.travel/mcp/sse with the header in their MCP settings. Connecting and searching are free; you pay only when a booking is completed. The README recommends models at an intelligence level equivalent to Claude Sonnet 4.6 or higher, and warns that weaker ones misread tool responses or hallucinate hotel data on complex requests.
Setup effort
Follow the published steps
USE CASES
01
Finding a hotel against awkward constraints
Search a district and price ceiling while filtering on the specifics — pets allowed, blackout curtains, a rain shower — instead of scrolling listings.
02
Booking the option you picked
Create the reservation for the chosen offer and hand the returned payment link to the traveller.
03
Checking a booking later
Look up the reservation status by its identifier without logging into anything.
04
Searching on accessibility requirements
Discover the valid accessibility filter values first, then search only properties that actually meet them.
05
Confirming the connection works
Run the authentication check when tools are not appearing, to separate a bad token from a client configuration problem.
6 tools
Listed in project docs. Your client may show a different list.
get_filterscreate_reservationget_reservation_statusechotest_mcp_authenticationBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
INSTALLATION
Connect your client
Server setup
Choose a connection method: Quick Connect — Fastest way — connect via Claude Desktop config in minutes [→ Quick Connect Guide](CONNECT_QUICK.md)
Connect with Skills (recommended) — Enhanced approach — install a skill for smarter, context-aware hotel search [→ Skills Setup Guide](CONNECT_WITH_SKILLS.md)
For Cursor / Windsurf and other remote-MCP clients: Just point them directly at https://mcp.winwin.travel/mcp/sse with your Authorization: Bearer <YOUR_TOKEN> header in your client's MCP settings.
Verify: Ask your AI: *"Use the test_mcp_authentication tool to check if WinWin.travel is connected."*
