Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Stay Otter

REMOTE · STAYOTTER.COM

Vetted stays, ground intelligence and price monitoring, with live totals and the block checked.

Available components

+10 this week 77 Trust /100

Last scanned (20 hours ago)

Scores higher than 69% of remote servers

Reachable. Last reached 5 Nov 2026.

Category E-commerce

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability56
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2672 tokens (~296/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
  • Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 70% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 3 Nov 26 0
    • Tool “search_stays” rewrote its description, which is the text the model reads security
  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 +7
    • Authorization: unverified → partial ▲ security
    • Tool “search_stays” rewrote its description, which is the text the model reads security
  • 31 Oct 26 0
    • “search_stays” reworded the description of “budget” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 30 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “check_listing” rewrote its description, which is the text the model reads security
    • Tool “get_block” rewrote its description, which is the text the model reads security
    • Tool “watch_booking” rewrote its description, which is the text the model reads security
    • Tool “watch_similar_homes” rewrote its description, which is the text the model reads security
    • “check_listing” reworded the description of “spot” cosmetic
    • “search_stays” reworded the description of “intent” cosmetic
    • “search_stays” reworded the description of “maxPerNightUsd” cosmetic
    • “search_stays” reworded the description of “nearLandmark” cosmetic
    • “search_stays” reworded the description of “travellerCountry” cosmetic
    • “watch_booking” reworded the description of “confirmation” cosmetic
    • Tool “check_listing” changed its title: Check a listing the traveller found → Check a listing the traveler found cosmetic
  • 29 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_block” rewrote its description, which is the text the model reads security
    • Tool “get_stay” rewrote its description, which is the text the model reads security
    • Tool “search_stays” rewrote its description, which is the text the model reads security
    • “search_stays” added an optional parameter “maxPerNightUsd” cosmetic
    • “search_stays” reworded the description of “budget” cosmetic
    • “search_stays” reworded the description of “maxTotalUsd” cosmetic
    • “search_stays” reworded the description of “stayType” cosmetic
  • 28 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 1.3.0 → 1.3.1 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://stayotter.com/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=stayotter.com CN=YR2,O=Let's Encrypt,C=US 6 Oct 2026 4 Jan 2027 RSA 2048 SHA256-RSA 683f7c657978fa6947e468308510b5d79fb
SANs: stayotter.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of stayotter.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
stayotter.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https:; font-src 'self' data:; connect-src 'self'; frame-src 'none'; frame-ancestors 'none'; object-src 'none'; base-uri 'self'; form-action 'self'; manifest-src 'self'; worker-src 'self' blob:; upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://stayotter.com/api/mcp Verified 200
http (plaintext) http://stayotter.com/api/mcp HTTPS enforced 308 https://stayotter.com/api/mcp
MCP tools · 9 exposed · ~2,092 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_listing ~214

Reads one place the traveler found themselves into the receipts a pick carries: where it is, whether the street is quiet or lively, bars, cafés and restaurants within a ten-minute walk, the distance to a spot they name and, with dates, the lowest total and the lowest they can still cancel, each read now. Takes a Booking.com, Vrbo or Expedia property page, or a hotel's name and city; Airbnb pages cannot be read. Needs a key: one check a day free, Pro up to thirty. 5 to 60 seconds.

NameTypeReqDescription
adultsinteger––
checkInstring–YYYY-MM-DD; with checkOut, prices are read too
checkOutstring––
citystring––
spotstring–A place they will walk to: 'Rainey Street', 'the convention center'
textstringyesA property page URL, or a hotel's name with its city after a comma: 'Hilton Austin, Austin'

No output schema declared.

No examples provided.

city_picks ~260

Instant and free: the latest finished standard search for one of the covered cities, about six weeks out, refreshed on a rota: whole homes for two adults and five nights in most cities, a six-adult weekend in New Orleans, Miami, Las Vegas, South Lake Tahoe, Sedona; stayType "hotel" gives the hotel-room trip (two adults, three nights) where one exists (Austin, Lisbon, Kyoto, Mexico City, New York, Paris, Barcelona, Montreal, San Diego, Edinburgh, Honolulu, London, Nashville, Scottsdale, New Orleans, Miami, Las Vegas, South Lake Tahoe, Sedona). Covered: Austin, Lisbon, Kyoto, Mexico City, New York, Paris, Barcelona, Montreal, San Diego, Edinburgh, Honolulu, London, Nashville, Scottsdale, New Orleans, Miami, Las Vegas, South Lake Tahoe, Sedona, Holbox, Niagara-on-the-Lake, Bentonville, Knoxville, Asheville, Canmore, Coeur d'Alene, Broken Bow, Lancaster, Ann Arbor, Da Nang, Hoi An. For other places or specific dates use search_stays.

NameTypeReqDescription
citystringyes–
stayTypestring–hotel for the hotel-room trip; whole homes by default

No output schema declared.

No examples provided.

get_activities ~93

Top-rated things to do on Viator for a search's spot and dates (what the trip is for first, the city's best otherwise), with a second place to look when the row is thin. Pass a searchId from search_stays or city_picks; intent overrides the search's own.

NameTypeReqDescription
intentstring–Override: 'kayaking', 'food tour'
searchIdstringyes–

No output schema declared.

No examples provided.

get_block ~173

Ground intelligence for one stay from a finished search: every bar and pub, café, restaurant and grocery within a ten-minute walk (counts, with + when the map read was capped in a dense center), the nearest stop and the walk to it, and map facts for walking back at night (bars within five minutes, the main road, the walk from the traveler's spot). Facts only: no crime figures, no safety rating. The same block is drawn as a map on the pick's stayUrl. Free; usually instant, a few seconds the first time a stay is asked about. Method: https://stayotter.com/ground.

NameTypeReqDescription
searchIdstringyesThe searchId from search_stays or get_stay
sourceIdstringyesThe pick's sourceId from the card

No output schema declared.

No examples provided.

get_stay ~177

The card for a search by searchId: finished picks with receipts, or its running status. Free and instant. Use it to finish a search_stays call that returned 'running', or to read a shared stay (https://stayotter.com/stay/s_…). Each pick's stay card page on the site also draws the block (venues by kind, groceries, nearest stop) and lists map facts for walking back at night; the method is at https://stayotter.com/ground. For a group deciding together, https://stayotter.com/vote/<searchId> is a no-account vote page on the picks.

NameTypeReqDescription
searchIdstringyesThe searchId from search_stays, or the id in a stayotter.com/stay/s_… link
travellerCountrystring––

No output schema declared.

No examples provided.

search_stays ~678

Live search of Booking.com, Vrbo and Expedia Group (hotel rooms) for the dates and party, verified against the map. Returns up to three picks (best overall, best value, closest) with receipts and tracked openUrl links. Picks within about a minute and the fine print after that, stopping at two and a half minutes; returns status 'running' with a searchId if it is not done within waitSeconds. Three trips on the house per connection, then a key (free account: five a month; Pro: unlimited).

NameTypeReqDescription
adultsinteger––
budgetstring–Super-cheap brands (Motel 6, Econo Lodge and the like) are out on every budget. value = cheapest that passes, mid = balanced, splurge = the nicest (ranked on star class and reviews, not price; no hot…
checkInstringyesYYYY-MM-DD
checkOutstringyesYYYY-MM-DD, 1 to 90 nights after checkIn (Booking.com is skipped past 30 nights; Vrbo quotes longer stays)
childreninteger––
flexDays––Date flexibility for the alert watcher: 0, 1, 2, 3 or 7 days
hotelBrandsarray–Hotel loyalty: keep hotel picks inside these groups (marriott, hilton, hyatt, ihg, accor, wyndham, choice, bestwestern); whole homes are unaffected
intentstring–What the trip is for, in the traveler's words: 'kayaking', 'a cooking class', 'a quiet writing week'. Steers things to do, never the ranking.
maxPerNightUsdnumber–Hard cap per night in US dollars, all-in (taxes and fees included); kept per night, so the stay total follows the dates. Use instead of maxTotalUsd when the traveler gives a nightly figure (the top o…
maxTotalUsdnumber–Hard cap on the whole-stay total in US dollars, taxes and fees included
nearLandmarkstring–A place the traveler wants to be near: 'Zilker Park', 'the old town', 'Shinkansen station'
petsboolean–A pet is coming: only listings whose own policy allows pets
quietStreetboolean––
stayTypestring–entire = whole apartments and houses (default); hotel = hotel rooms (Booking.com and Expedia Group); any = rentals and hotel rooms side by side, each tagged; resort = resorts and all-inclusives, Book…
travellerCountrystring–ISO-2 country the traveler lives in (default US); decides whether an eSIM line applies
vibestring––
waitSecondsinteger–How long to wait for the search before returning a running status
walkToarray–What should be within a ten-minute walk
wherestringyesCity or town, with state or country when ambiguous: 'Lisbon', 'Wimberley, TX', 'Kyoto, Japan'.

No output schema declared.

No examples provided.

set_alert ~74

Starts the otter's daily re-run of a finished search, emailing the key's account when a verified pick drops 5% or $50 or the cheapest pick disappears. Needs a key (stayotter.com/connect); the first alert is free with an account, more are Pro.

NameTypeReqDescription
searchIdstringyes–

No output schema declared.

No examples provided.

watch_booking ~276

For a stay already booked with free cancellation: pass the confirmation email's text. The otter keeps five facts (property, dates, total paid, deadline, where it was booked), discards the rest (no names, confirmation numbers or card details), reads the property's rate every morning and emails the account when a cheaper rate it can still cancel into appears (5% or $50), with reminders 7, 3 and 1 days before the deadline. Hotels booked direct are read across sellers through Google's rate list. A single whole home has one calendar, so once booked its price can't drop for the traveler: the first read finds the nights taken, the otter emails to say so and offers (free) to watch other whole homes nearby for the same dates until the deadline. A watch that closes without a drop ends with one note saying the price held (the reads and the lowest rate seen); a drop alert asks whether the traveler rebooked, and the answers feed the public track record as totals. Needs a key; free and unlimited. The otter never books or cancels.

NameTypeReqDescription
confirmationstringyesThe confirmation email's text, as the traveler pasted or forwarded it
paidUsdnumber–What they paid in US dollars, when the confirmation is in a currency the otter can't convert

No output schema declared.

No examples provided.

watch_similar_homes ~147

For a whole home already booked (watch_booking, then the first morning's read found the nights taken by the traveler): watches other verified whole homes nearby for the same dates and party, and emails the account when one comes in at least 5% or $50 under what they paid, until their free-cancellation deadline. A find is always a different home, never the same one cheaper; the traveler books the new one first and cancels theirs second. Starts with one live search now (30 to 90 seconds; not counted as a trip). Needs the key the booking was watched with; free.

NameTypeReqDescription
bookedIdstringyesThe bookedId watch_booking returned

No output schema declared.

No examples provided.

Install

How do I install the Stay Otter MCP server?

Stay Otter is a hosted endpoint at https://stayotter.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · stayotter.com

# add to Claude Code
claude mcp add --transport http com-stayotter-stay-otter 'https://stayotter.com/api/mcp'
Common questions

What is the Stay Otter MCP server?

Stay Otter is an MCP server listed in the public MCP registry as com.stayotter/stay-otter. Vetted stays, ground intelligence and price monitoring, with live totals and the block checked. This page covers its hosted endpoint (https://stayotter.com/api/mcp).

Is the Stay Otter MCP server safe to use?

Stay Otter scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Stay Otter MCP server expose?

Stay Otter exposes 9 tools: search_stays, get_stay, city_picks, get_activities, set_alert, and 4 more. Their descriptions and schemas cost roughly 2,092 tokens of context every time the server is loaded.

Does the Stay Otter MCP server require authentication?

No. We connected to Stay Otter without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Stay Otter MCP server still maintained?

Stay Otter is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Stay Otter MCP server?

VerifyMCP ran 13 checks on Stay Otter, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.