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/booking-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/booking-mcp/hasdata-booking)<a href="https://agentmods.dev/rules/hasdata/booking-mcp/hasdata-booking"><img src="https://agentmods.dev/badge/rules/hasdata/booking-mcp/hasdata-booking/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/booking-mcp/hasdata-booking"><img src="https://agentmods.dev/badge/rules/hasdata/booking-mcp/hasdata-booking.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 | $0.00016 | $0.00628 |
| Opus 5.5 | $0.00006 | $0.00251 |
| Sonnet 5.5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
hasdata-booking 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Booking.com through HasData
Two tools, and both demand a full stay. hasdata_booking_search_getBookingSearchResults needs keyword, checkInDate, checkOutDate, rooms, adults and children. hasdata_booking_place_getBookingPlaceDetails needs the same six with the property url in place of the keyword.
There is no way to ask what a hotel costs in general. Every answer belongs to a date range and a party.
Narrowing
sort orders the set and price_min_ and price_max_ bound it. bedrooms and bathrooms set minimum counts on any property rather than filtering to apartments.
language changes how the answer is written. currency normally does too, but a price band is read in the selected currency, so with price_min_ or price_max_ set it also changes which properties come back.
children and childrenAges travel together. Booking prices a child by age, so a count without ages returns a different set than the guest would see.
Two scores that look alike
rating is the official star rating, so it runs to 5. reviews.score is the guest score, so it runs to 10, alongside reviews.count and a secondaryScore for a single topic such as location. A summary that treats a 3 and a 9.4 as the same scale is nonsense.
Reading the price
The keys carry suffixes. pricePerStayRaw is the string and pricePerStayParsed the number, and the same pattern holds for the rest.
pricePerStayParsed is not what the guest pays. Most results also carry excludedChargesParsed, the part Booking bills on arrival, so the real total is the two added together. Test for it, because a result can omit the pair, and a missing pair means nothing was parsed rather than that the charges are zero.
A discount pair appears only when the property is discounted, and it is spelled discountRaw and discountParsed. Earlier releases misspelled it as dicsount*, so code written against that spelling now reads nothing and reports no discount.
A destination and a window with nothing open returns a successful result with an empty results array. Say the dates are full rather than reporting the place as missing.
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.
- 3d ago Changed · +4 lines fc383e22ca83
- 23d ago First seen · 35 lines · 16 tokens per session scan A cb8a7f2e4db9
hasdata-booking is a cursor rule published in the GitHub repository HasData/booking-mcp (11 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 628 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-instagram
How to pull public Instagram profiles and post feeds through the HasData MCP server.
hasdata-zillow
How to pull Zillow listings and property details through the HasData MCP server.
hasdata-indeed
How to pull Indeed job listings and postings through the HasData MCP server.
hasdata-tiktok
How to pull TikTok profiles, post feeds, keyword search and comments through the HasData MCP server.
hasdata-airbnb
How to pull Airbnb stays and listing details through the HasData MCP server.
hasdata-duckduckgo
How to pull DuckDuckGo results and the Search Assist answer through the HasData MCP server.