Apaleo MCP Server use climbs 70% as AI agents enter live work

By Daniel Okafor

Apaleo said usage of its Model Context Protocol (MCP) Server rose 70% from July through September 2026, as hotels deployed AI agents for bulk reservation changes, forecasting and rate management in live operations.

Growth accelerated late in the period: usage rose 23% from July to August and 38% from August to September. Apaleo said adoption was spread evenly across its customer base rather than concentrated among large, technology-forward groups.

What does the growth show?

Apaleo launched what it called the first MCP Server in the hotel property-management category in September 2025. Usage has climbed steadily since, with the sharpest increase arriving in the July-September 2026 quarter.

Comparable adoption spans independent and family-run hotels without engineering teams and enterprise groups operating rooms and apartments at portfolio scale.

The h2c Hotel Chain Tech Report 2026 found that 91% of hotel chains now use AI, up 13 percentage points from 78% a year earlier; only 15% have implemented a standardized AI data-access layer such as MCP.

Another 52% have no plans to add one, while 38% cite integration with existing systems as a barrier. Reliance on AI rose from 4.7 to 5.4 on a 10-point scale over the past year, while trust held flat at 6.5.

What does the server replace?

The open MCP standard gives an AI agent one consistent route to live property data and permission to act on reservations, rates, availability and guest profiles, replacing a custom connection for every AI tool a hotel wants to use.

Apaleo’s server extends that standard across its platform. Agents work through one connection, under the acting user’s permissions and with a full audit trail. Governance matters more as agents take on additional work.

Chat interfaces make the server usable without code: hoteliers describe a change in plain language, and the agent executes it in the underlying system. That lower barrier lets hotels without engineering teams build their own agents.

Model choice matters too. Most property-management systems determine which assistant an operator can enable, while Apaleo says customers can connect their preferred model and switch as tools improve.

The h2c data show external tools such as ChatGPT account for 60% of hotel chains’ day-to-day AI use, against 27% for AI embedded in vendor systems.

Where does the time go?

• Appenzeller Hotels: The three-property group in Switzerland runs a daily Claude revenue workflow that identifies bookings eligible for upgrades to free lower room categories for resale, saving about two hours a week alongside booking reconciliation and reporting.
• Brera Serviced Apartments: It added its own MCP alongside Apaleo’s and built a data lake combining revenue and cost data. Last year’s balance sheet generated a forecast for both halves of this year and sent it to the controller for budgeting; three people previously spent two weeks on that work.
• McDreams Hotels: The German mid-market group automates repetitive tasks and answers routine questions that previously required reports, with staff querying their own data several times daily.
• LikeStay: It uses the MCP Server with AI to turn existing price lists into rate plans, analyze reservation patterns and speed property-management-system migrations, moving data from other systems onto its Apaleo stack within hours.
• Smartments: The enterprise operator used the server to amend about 2,000 reservations in one action, work that otherwise would have required roughly 50 hours.

These deployments remain concentrated in staff-facing work, where accountability sits with the team rather than the guest. Operators typically begin with a contained task, then expand as they identify more work to delegate.

Christoph Klein, chief marketing officer at McDreams Hotels, said: “We can automate repetitive processes, get relevant information faster, and use AI to help with questions that would otherwise take hours to answer.”

Klein added: “We’re still on a journey, but the potential is not just about saving time. It’s about making better use of the data we already have.”

What changes for operators?

Philip von Ditfurth, founder of Apaleo, said: “A year ago, hoteliers were asking whether AI agents could do real work. Now they are asking how quickly they can hand more over. What changed is access. Once an operator can point an agent at live reservations, rates and guest data, the work gets done.”

He added: “We are seeing PMS migrations that used to take weeks run in hours, and forecasting work that occupied three people for a fortnight come back the same day. Most hoteliers have already picked the AI they want to use.”

“The question is whether their systems let them connect it, and too often the vendor decides that for them,” von Ditfurth said.

Apaleo, an API-first property-management platform, said it powers more than 2,200 properties in more than 30 countries spanning hotels, vacation rentals, serviced apartments and residential living. Customers include citizenM, easyHotel, limehome, Korner Hotels, Miiro Hotels and Numa.

Hospitality businesses can join the company’s MCP group through the Apaleo Community. Apaleo also operates Agent Hub, which it calls the first AI-agent marketplace for hospitality and says helps operators adopt autonomous agents. The company won Phocuswright’s 2025 EMEA Travel Innovation Award.

The practical change is not merely a faster chatbot. Operators can delegate bounded tasks against live systems while retaining permissions and audit trails. With 38% citing integration as a barrier and 52% reporting no plan for a standard layer, the next test is whether property-management vendors can widen access without weakening control.