Ask Claude or ChatGPT about inquiries, bookings, calendars, guest messages and housekeeping jobs in Hostfully, and have it reply, block dates or close out a job.
Read from Hostfully when someone asks. Nothing exported, nothing copied, and changes only where you allow them.
Which inquiries are still waiting for our reply, and since when?
Which of our properties are free for the last week of July, and what would a stay for six cost at the Lake Cabin?
Block the Lake Cabin from August 3 to 6 for maintenance.
Properties, pricing and money stay read-only. Cancel, decline, close, ignore and delete are each their own permission. Every write is on record.
Inquiries come in on every channel, the calendar decides what you can say yes to, and the turnover jobs have to keep up. Connected once, your team can ask which inquiries are still unanswered, what is open next month across every property or which reviews need a reply, and the AI can answer the guest, block the dates or mark the job done, if you allow it.
An admin connects Hostfully one time. Nobody hands over a personal login.
Each answer is read at the moment of the question. Nothing is exported or copied, so there is nothing to keep in sync.
What each role can see and do holds in every AI your team uses, and in your own agents.
Every question and every action, by every person and agent, in one audit trail.
Yes. A message is sent the moment it is created, by email or through the guest's booking channel, and the reply shows whether it was delivered. Sending is its own permission.
No. Properties, pricing rules, fees and channel settings are read-only here, and so are orders and transactions. It works on the day to day: leads, messages, calendars, reviews and jobs.
From Hostfully's orders, not the bookings list: it takes the booked stays in the period, adds up their orders in each order's currency, and uses transactions for the cash actually received.
Yes, and one built for a whole company. FrontierOps gives Claude, ChatGPT and any other MCP client one connection to Hostfully, set up once by an admin. What each role can read or change is decided in FrontierOps, and every call is on record, instead of each person running their own server with their own login.
A direct connection links one AI to Hostfully through one person’s login, with that person’s settings. That works for one person. For a team it means no shared definitions, no single place to decide who can see or change what, and starting over when you switch AI. Through FrontierOps, Hostfully is connected once, for every AI and every agent, under one set of permissions, with every call on record.