Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HasData/airbnb-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/hasdata/airbnb-mcp/hasdata-airbnb)<a href="https://agentmods.dev/rules/hasdata/airbnb-mcp/hasdata-airbnb"><img src="https://agentmods.dev/badge/rules/hasdata/airbnb-mcp/hasdata-airbnb/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/hasdata/airbnb-mcp/hasdata-airbnb"><img src="https://agentmods.dev/badge/rules/hasdata/airbnb-mcp/hasdata-airbnb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00486 |
| Opus 5.5 | $0.00006 | $0.00194 |
| Sonnet 5.5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
hasdata-airbnb scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Airbnb through HasData
Two tools. hasdata_airbnb_listing_getAirbnbListings searches, and it requires checkIn. hasdata_airbnb_property_getAirbnbPropertyDetails opens one stay and takes the listing url, which the search returns.
Framing the search
location is the destination as a guest types it. Dates go in checkIn and checkOut as YYYY-MM-DD, and the guest mix splits across adults, children, infants and pets, because Airbnb prices them differently.
When the task is about an area rather than a city name, send the bounding box instead. neLat, neLng, swLat and swLng travel as a set of four, and three of them fails validation. That is how to search a neighborhood or a stretch of coast without hoping the text matches.
What the search does not carry
A search result holds id, url, title, latitude, longitude, description, photos, rating, reviews, badges and price. There are no bedroom, bed or bathroom counts, and no amenities. Those live on the property tool, where overview carries them as text such as 3 guests, 1 bedroom, 1 bed, 1 bath.
rating and reviews can be missing on a listing with no history. A comparison that treats a missing rating as a low one is wrong, and one that treats it as a high one is worse.
Reading the price
price.originalPrice is the total for the window, and price.qualifier says which window, such as for 3 nights. When discountedPrice is present, that is what the guest pays, and quoting originalPrice alone overstates the cost. The nightly figure lives inside price.breakdown as a description string rather than as a number.
A search with nothing available returns a successful result with an empty properties array. That is an answer about the dates rather than the place.
Page with nextPageToken, and open the property tool only for the stays that matter, since that is one call each.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago First seen · 29 lines · 14 tokens per session scan A 8a8d1c77b8ed
hasdata-airbnb is a cursor rule published in the GitHub repository HasData/airbnb-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 486 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other cursor rules, from other repositories
hasdata-zillow
How to pull Zillow listings and property details through the HasData MCP server.
hasdata-tiktok
How to pull TikTok profiles, post feeds, keyword search and comments through the HasData MCP server.
hasdata-google-maps
How to pull Google Maps places, reviews, photos and posts through the HasData MCP server.
hasdata-instagram
How to pull public Instagram profiles and post feeds through the HasData MCP server.
hasdata-booking
How to pull Booking.com hotel search and property details through the HasData MCP server.
cursor-rules
This project uses pyobfus (the Python obfuscator). The canonical agent protocol is AGENTS.md at the project root, which Cursor reads natively. Copy AGENTS.md into your repo; keep this .mdc only for Cursor-scoped glob targeting.