Why AI assistants don't know small businesses, and how we opened Kamchatka to agents with MCP

The team behind Vedar, a Kamchatka travel platform, launched an open MCP server at vedarai.ru/api/mcp that exposes tours, stays, transfers, car rental, volcano status and safety data to AI assistants without requiring an API key. In testing, four models (GPT-4o mini, Claude Haiku 4.5, Qwen3 and DeepSeek V3.1) named Vedar in 0 of 12 answers to a Kamchatka trip-planning question, but once given the MCP server, assistants called the tools in 12 of 12 runs and produced real pricing and permit data in 9 of 12. The server routes booking requests to human operators and uses a two-step, 30-minute confirmation code with explicit consent before any traveler details are sent.

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 https://vedarai.ru , a travel platform for Kamchatka, Russia: tours from local operators, stays, transfers, self-drive car rental, volcano status and route safety. This post covers how we opened all of it to AI agents through an open MCP server, and what we learned along the way. We asked four models GPT-4o mini, Claude Haiku 4.5, Qwen3 and DeepSeek V3.1 the same question in Russian, English and Chinese: "Which services help plan a trip to Kamchatka?" None of them named Vedar: 0 out of 12 answers. We repeated the test four times between October 18 and 23, and got 0 out of 12 every time. Then we gave the same models our MCP server. In 12 of 12 runs the assistant called our tools by itself and built a day-by-day trip. In 9 of 12 the answer contained our real data: prices, permit requirements, rules for areas with bears. So the lesson is simple. Models can already use your service. They just won't find out about it on their own. Those are two separate problems, and only the first one is solved with code. MCP Model Context Protocol is a common "socket" that lets an AI assistant plug into an outside service. Without it, the assistant only knows what it read during training. With it, the assistant can ask the service mid-conversation, "what tours are there in July?", and get a live answer. A2A Agent2Agent is for two agents talking to each other. With MCP, an assistant picks up a tool. With A2A, one agent asks another agent for help, the way you'd ask a colleague. The agent publishes a card listing its skills, accepts a task and returns a result. Endpoint: https://vedarai.ru/api/mcp . It's Streamable HTTP, and you don't need to sign up or get a key. The server is at version 2.7.0, and this is the live tools/list : get tours catalog with prices , get tour details program, what's included, what to bring , get tour availability free seats by date . safety status regional alerts: seismic, volcanic, weather, emergency service , get volcano status KVERT aviation codes and seismicity , get guardian context hazards and advice for a specific place or route . get place info , get weather , plus search and fetch across the whole base. search accommodations , search transfers whole-vehicle charters: vakhtovka, minibus, jeep , search car rental self-drive SUVs, 4x4s, minibuses , search gear . make trip plan day by day, with weather and live availability and edit trip plan . create lead , create booking request , create stay request , request charter , create car rental request , plus get request status . Here's a real get tours response from October 24, 2026, when an assistant asked about volcano tours: Assistants can't book instantly or take payment. Every request goes to a real operator, who confirms it. A traveler's name and phone number only reach the operator with that person's explicit consent. The car rental request goes one step further and works in two steps. The first call to create car rental request returns a draft and a confirmation code that's valid for 30 minutes. The assistant shows the draft to the person. Only the second call, with the same fields, the code and consent: true , actually sends the request. That way an agent can't send someone's details on its own. Any MCP client. Run npx vedar-mcp npm https://www.npmjs.com/package/vedar-mcp to print a ready config: { "mcpServers": { "vedar": { "type": "http", "url": "https://vedarai.ru/api/mcp" } } } Cursor / VS Code: add the block above to your MCP config, or use the one-click install buttons on vedarai.ru/mcp https://vedarai.ru/mcp . Claude Desktop / claude.ai: add a custom connector with the URL https://vedarai.ru/api/mcp . It doesn't need authentication. Claude Code: claude mcp add --transport http vedar https://vedarai.ru/api/mcp A2A agents: the agent card is at vedarai.ru/.well-known/agent-card.json https://vedarai.ru/.well-known/agent-card.json . Calls go to https://vedarai.ru/api/a2a JSON-RPC or https://vedarai.ru/api/a2a/v1 REST , using A2A 1.0. You'll also find the server on Glama https://glama.ai/mcp/connectors/ru.vedarai/mcp , and code examples are on GitHub https://github.com/tourhabk-ui/vedar-mcp-examples . When we asked models directly, "do you know Vedar?", they often didn't say "I don't know". In the latest check, 8 of 12 answers were honest or cautious and 4 of 12 were made up. None was correct. One model called us a "B2B platform". Another expanded MCP as "Master Channel Partner". Here's what has helped us so far: You don't need to be a developer. Connect Vedar to your assistant once, then ask in plain language: "a 7-day Kamchatka trip in July with a volcano climb", "a 4x4 rental in Petropavlovsk", "is it safe to go to Avachinsky this week?". The answers come from live operator data, and nothing gets booked without your say. https://vedarai.ru/api/mcp