Why AI assistants don't know small businesses, and how we opened Kamchatka to agents with MCP
AI assistants are getting good at planning trips. Ask one about Kamchatka, though, and you get Booking, Viator, GetYourGuide and a few generic tour agencies. The small local operators who actually run the volcano climbs and the bear-watching trips mostly don't show up. We build Vedar ( vedarai.ru ), a travel platform for Kamchatka, Russia: tours from local operators, stays, transfers, self-drive…
AI assistants excel at handling large-scale trip planning, yet they struggle to recommend local tour operators in specific destinations like Kamchatka. A travel platform called Vedar has been developed to connect such small businesses with AI agents. Vedar features 22 tools for managing tours, accommodations, vehicle rentals, and safety information.
By implementing an open Model Context Protocol (MCP) server, Vedar allows AI agents to directly access its data and services. When queried about Kamchatka trips, multiple AI models consistently returned Vedar as a relevant service provider. However, without MCP integration, AI assistants would typically only retrieve generic tour information without the specific, local insights offered by Vedar.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
