Why AI assistants don't know small businesses, and how we opened Kamchatka to agents with MCP
Описание и применение
Интеграция Vedar через MCP позволила ИИ‑ассистентам обнаруживать и использовать сервисы малого бизнеса, предоставляя точные данные о путешествиях и соблюдая согласие пользователя.
Задача
AI assistants fail to discover small local operators like Vedar when planning trips to niche destinations such as Kamchatka.
Результат
Integrating Vedar via MCP enabled AI assistants to discover and use a small‑business travel platform, providing accurate, live trip data and respecting user consent for bookings.
Рабочий процесс
- 1. Test models with a query about Kamchatka services in multiple languages. 2. Observe no mention of Vedar. 3. Provide models with Vedar’s MCP endpoint. 4. Run the same queries; models call tools and return live data. 5. Verify that data includes prices, availability, safety alerts, and booking requests. 6. Document consent flow for booking requests.
- 7. Publish MCP configuration and agent card for integration.
- 8. Encourage travelers to ask plain‑language questions and receive live operator data.
Доказательства
None of them named Vedar: 0 out of 12 answers.
In 12 of 12 runs the assistant called our tools by itself and built a day‑by‑day trip.
Assistants can't book instantly or take payment. Every request goes to a real operator, who confirms it.
- Дата записи: 2026-10-24T00:26:20.600Z