Use ToddlerVacation.com from AI agents
The whole directory is open to ChatGPT, Claude and other assistants: search hotels as tools over MCP, call a free JSON API, or read any page as markdown. No key, no sign-up.
What the data means
Ratings are guest ratings out of 10, averaged from TripAdvisor, Google and Booking. There is no separate toddler score. Prices are bands per night in USD. Amenities are as listed by each hotel. We don’t take bookings; each hotel links to its own site.
MCP server
For assistants that support the Model Context Protocol.
Endpoint: https://toddlervacation.com/mcp (Streamable HTTP, stateless, no authentication). Server card: /.well-known/mcp/server-card.json.
- Claude: Settings → Connectors → Add custom connector, and paste
https://toddlervacation.com/mcp. - ChatGPT: in developer mode, add a connector with the same URL.
- Claude Code and other clients: add a remote HTTP server pointing at the URL above.
| Tool | What it does |
|---|---|
search_hotels | Find hotels that work for families with a baby or toddler. Filter by place, trip type, toddler amenities (cot, high chair, kids menu, kids club, kids pool, babysitting, stroller), price band and guest rating. Results are sorted by guest rating (out of 10) and include a link to each hotel page. |
get_hotel | Full details for one hotel by its slug: location, nearest airport, guest ratings per review site, price band, and every toddler amenity (baby gear, safety, food, play, services) plus the link to book on the hotel’s own site. |
list_destinations | All countries in the directory with how many toddler-friendly hotels each has and its regions. |
get_destination | A destination’s practical facts for families (main airport, time zone, language, currency, best months, regions, toddler-friendly facilities) and its hotels. |
list_trip_types | Trip types (beach, city, nature, cruise, camping, adventure parks) with what to look for with a toddler: where to stay, amenities, activities, safety, packing list, healthcare and getting around. |
list_guides | Travel guides for parents: packing lists, flying with a toddler and planning advice. |
get_guide | The full text of one travel guide, as markdown. |
curl -s https://toddlervacation.com/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
"params":{"name":"search_hotels","arguments":{"country":"Portugal","amenities":["cot"]}}}'JSON API
Base URL /api/v1. Described in OpenAPI 3.1.
GET /api/v1/hotels: search, withquery,country,city,trip_type,amenities(comma-separated),max_price_band,min_guest_rating,limit,offsetGET /api/v1/hotels/{slug}: one hotel with every toddler amenityGET /api/v1/destinationsand/destinations/{slug}GET /api/v1/trip-typesand/trip-types/{slug}GET /api/v1/guidesand/guides/{slug}GET /api/v1/health: status
curl -s 'https://toddlervacation.com/api/v1/hotels?country=Portugal&amenities=cot,high%20chair&max_price_band=200-300'
Markdown pages
The cheapest way for a model to read the site.
Every page has a markdown twin. Append .md to the URL (/hotels.md, /index.md) or request any page with Accept: text/markdown. Responses include an x-markdown-tokens estimate. Start from /llms.txt.
curl -s -H 'Accept: text/markdown' https://toddlervacation.com/destinations/portugal
Discovery files
- /llms.txtSite index for language models (llmstxt.org)
- /llms-full.txtEvery hotel, destination, trip type and guide in one file
- /openapi.jsonOpenAPI 3.1 description of the JSON API
- /.well-known/api-catalogAPI catalog (RFC 9727)
- /.well-known/mcp/server-card.jsonMCP server card
- /.well-known/agent-skills/index.jsonAgent Skills index, with a trip-planning skill
- /.well-known/ai-catalog.jsonAgentic Resource Discovery (ARD) catalog
- /robots.txtCrawl rules, AI crawler rules and Content Signals
Questions
Is there a rate limit?
There is no key and no fixed quota. Responses are cached for a few minutes, so please cache on your side too and keep requests reasonable.
Can I use the content in AI answers and training?
Yes. Our robots.txt Content Signals allow search, AI answers and training. Please link back to the hotel or guide page you use.
How fresh is the data?
The API, MCP server and markdown pages read the same source as the website, refreshed every few minutes.