MCP Integration

Search hotels from your AI

Trip1 supports the Model Context Protocol (MCP), so AI assistants like Claude can search and book hotels without leaving your conversation.

What is MCP?

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external services. Instead of just answering questions, your AI can do things, like search for hotels on Trip1.

When you add Trip1 as an MCP server, your AI assistant gets access to our hotel search. Ask it to find a hotel in Tokyo next week and it'll come back with real prices and booking links.

Setup

Setup for the most common tools:

Claude Desktop

Go to Settings → Connectors → Add custom connector and enter:

https://trip1.com/api/mcp

Claude Code

Run in your terminal:

claude mcp add --transport http trip1 https://trip1.com/api/mcp

Cursor

Open Settings → Tools & MCP → Add new MCP server and add:

{
  "mcpServers": {
    "trip1": {
      "url": "https://trip1.com/api/mcp"
    }
  }
}

Or create/edit .cursor/mcp.json in your project with the same config.

Any MCP-compatible client

Our endpoint supports Streamable HTTP at:

https://trip1.com/api/mcp

No authentication required. Our server card is available at the standard well-known endpoint:

https://trip1.com/.well-known/mcp.json

What you can do

Right now, the Trip1 MCP server exposes one tool: search_hotels. It takes a location, dates, and guest or room counts. It returns available hotels with prices and photos.

Ask your AI:

"Find me a hotel in Barcelona, March 15-20, for 2 people."

That becomes:

{
  "name": "search_hotels",
  "arguments": {
    "location": "Barcelona",
    "checkIn": "2026-03-15",
    "checkOut": "2026-03-20",
    "guests": 2,
    "rooms": 1
  }
}

You get back hotels with prices, photos, and links to book on Trip1.

Try it out

Add Trip1 to your AI assistant and start searching hotels in seconds.

Learn more about MCP