The Airbnb Search MCP server (from OpenBnB) lets an AI model search Airbnb listings by location, dates and filters, then pull the full details for any result. It works without an API key by respecting Airbnb's public search, making it a simple building block for travel-planning and comparison agents.
Bring your own
Claude Sonnet 4.5
MCP Playground runs 40+ models on the same workflow: switch anytime, or use Compare mode to run several in parallel and balance quality vs. cost.
No token required
How models use it and what it is built for.
The Airbnb MCP server exposes two MCP tools built on Airbnb's public search. One searches listings for a location with check-in/check-out dates, guest counts and filters, returning results with prices and links; the other fetches the full details for a specific listing — amenities, house rules, ratings and more. It runs as a Node.js stdio process and needs no credentials. It honours Airbnb's robots directives by default, so it is intended for personal trip planning and research rather than bulk scraping. For a travel agent, it turns "find me a place" into structured, comparable results the model can reason over.
Typical tools an AI model can call. Exact names vary by version.
Copy any of these into MCP Agent Studio after connecting.
Find Airbnb listings in Lisbon for two adults, check-in 12 Aug, check-out 16 Aug, under €150 a night.
Compare the top three results and tell me which has the best rating-to-price ratio.
Get the full details for this listing and list its amenities and house rules.
Search for pet-friendly places near Austin for a weekend in September and summarise the options.
This is not a single-model product: you get the same MCP connection with 40+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.
Default pick for Airbnb Search
Claude Sonnet 4.5
Claude Sonnet 4.5 handles multi-step trip planning — searching, comparing and pulling details — reliably. Haiku 4.5 is fine for a single search-and-summarise request.
Open MCP Agent Studio with the connection pre-filled. Add your token, pick any of 40+ models, and start chatting — no install required.
Open Agent StudioCommon questions about connecting, scoping and using it safely.
It is an open-source MCP server from OpenBnB that lets AI models search Airbnb listings and fetch listing details through the Model Context Protocol. It works without an API key by using Airbnb's public search.
Two tools: airbnb_search to find listings by location, dates, guests and filters (returning prices and links), and airbnb_listing_details to fetch the full details of a specific listing, including amenities, house rules and ratings.
No. It uses Airbnb's public search and requires no credentials, so you can deploy and query it immediately. It respects Airbnb's robots directives by default.
Yes, for personal trip planning and research. It is not intended for bulk scraping or commercial data harvesting — keep usage to the kind of searching a person would do when booking a stay.
Open MCP Agent Studio, deploy the hosted Airbnb server from the catalog (no key needed), pick a model and describe the trip. You can watch each airbnb_search and airbnb_listing_details call and its results live.
Brave Search
Give an AI agent live web and local search via the Brave Search API.
Tavily
Search, extract and crawl the web for AI research agents via Tavily.
Wikipedia
Ground AI answers in verifiable Wikipedia articles — no API key needed.
Hacker News
Search and read Hacker News stories, comments and users from an AI agent.
