OKstays

Connect it to your AI

Claude Code

claude mcp add --transport http okstays https://okstays.com/api/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://okstays.com/api/mcp

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "okstays": {
      "url": "https://okstays.com/api/mcp"
    }
  }
}

Tools it offers

8 tools, as the server itself reported during our check on Oct 31, 2026.

• search_hotelsRank hotels in a city by the OKstays Comfort Score (0-10 from comfort signals; cleanliness, beds, shower, bugs and safety count 40%). Only hotels that pass all five must-haves are returned. Optionally rank for a travel s
• get_hotelOne hotel in depth: Comfort Score breakdown, what the scores rest on, the five must-haves, its strengths and complaints with the reason behind each score, price and links. Pass focus with what the user asked about; detai
• list_citiesDestinations covered, with hotel counts. Optionally only those in one country.
• get_filtersAll comfort filters (ids, names, descriptions, categories) usable in search_hotels, plus the travel styles (personas).
• compare_hotelsCompare 2-4 hotels side by side: Comfort Score breakdown, price, strengths, caveats, the filters where they differ most, and a verdict (best comfort, cheapest, best value).
• find_similar_hotelsHotels in the same city with the comfort profile closest to a given hotel (similar scores across the comfort filters). Use cheaper_only for 'like this one but cheaper'.
• get_city_overviewSnapshot of a destination: hotel counts, average Comfort Score, median price, where its hotels beat and trail the average hotel, the best neighbourhoods, and which travel styles it suits. Use it when the user is choosing
• plan_tripHotels for a multi-stop trip, one stay per destination in travel order (e.g. Lisbon 4 nights, Porto 3, Madrid 5): the best match for each stop by the OKstays Comfort Score (or the travel style's score), alternatives, the

Questions