Lonely Planet MCP server for AI agents
Let Claude, ChatGPT or your own agent read Lonely Planet: 1 typed function through one MCP server. No Lonely Planet API key needed.
- Site
- lonelyplanet.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Lonely Planet
An MCP server for Lonely Planet alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/lonelyplanetEvery site
One MCP server for Lonely Planet and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
searchSearches lonelyplanet.com's site-wide index.Arguments
Name Type Required querystringYes Returns
LonelyPlanetSearchResult[]interface LonelyPlanetSearchResult { title: string; subtitle: string | null; collection: string; // e.g. "destinationAssemblies", "products", "journeysItineraries" url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/lonelyplanet/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.lonelyplanet.search("rome");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.lonelyplanet.search("rome"))curl -X POST https://api.bowmark.ai/v1/sites/lonelyplanet/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"rome"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.lonelyplanet.search("rome");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/lonelyplanet/<function> - OpenAPI
/v1/sites/lonelyplanet/openapi.json