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/commands/hasdata/airbnb-mcp/stay-shortlist)<a href="https://agentmods.dev/commands/hasdata/airbnb-mcp/stay-shortlist"><img src="https://agentmods.dev/badge/commands/hasdata/airbnb-mcp/stay-shortlist/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/commands/hasdata/airbnb-mcp/stay-shortlist"><img src="https://agentmods.dev/badge/commands/hasdata/airbnb-mcp/stay-shortlist.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 | $0.00013 | $0.00348 |
| Opus 5.5 | $0.00005 | $0.00139 |
| Sonnet 5.5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
stay-shortlist 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
Build a shortlist of places to stay.
Ask me for the destination, the dates and who is travelling if I have not given them. Guest counts matter to the price, so do not assume two adults.
Then:
- Call
hasdata_airbnb_listing_getAirbnbListingswithlocation,checkIn,checkOutand the guest split acrossadults,children,infantsandpets. - Report how many stays came back before filtering. An empty result means those dates, not that place, and I need to hear that plainly.
- Shortlist five: title, the stay total from
price.originalPricewith the window fromprice.qualifier, thediscountedPricewhen the listing carries one,ratingwithreviews, and the listing URL. Do not report bed or bathroom counts here, because the search does not return them. - Flag anything rated under 4.5 or with fewer than ten reviews. Treat a listing with no
ratingat all as unrated and say so, rather than letting it pass the filter because the field was missing. - Open
hasdata_airbnb_property_getAirbnbPropertyDetailsonly for the stays I pick. Reportoverview, which is where the guest, bedroom, bed and bath counts live, the amenities whoseavailableis true, anything insafetyAndPropertyInfo, the host record, and what the host says in the description.
Quote prices for the window I asked about, and say so. A nightly rate without its dates is a number I cannot use.
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 · 18 lines · 13 tokens per session scan A 62071290f6ff
stay-shortlist is a command published in the GitHub repository HasData/airbnb-mcp (8 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 348 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 commands, from other repositories
zillow-comps
Comparable sales for an address or an area, pulled from Zillow.
tiktok-pulse
What an account posts on TikTok and which videos actually performed.
local-leads
A contact list of local businesses for a category and a city, from Google Maps.
profile-brief
A brief on a public Instagram account and what it has been posting.
hotel-shortlist
A shortlist of Booking.com hotels for a destination, dates and party.
hiring-map
Who is hiring for a role across several cities, with salaries where employers publish them.