Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Stay Otter is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Vetted stays, ground intelligence and price monitoring, with live totals and the block checked.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http stay-otter-mcp https://stayotter.com/api/mcp
# 2 — ask your agent for something these tools do
# search_stays, get_stay, city_picks and 4 more
Stay Otter costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
STAll 1 server
stayotter1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http stay-otter-mcp https://stayotter.com/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take Authorization header (Optional. Bearer so_live_… key from stayotter.com/account; without it, three trips per connection.) if you want to set it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Live search of Booking.com, Vrbo and Expedia (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. Takes 30 to 90 seconds; returns status 'running' with a searchId if it is not done within waitSeconds. Three searches on the house per connection, then a key (free account: 10 a month; Pr
| Parameter | Type | Required | Notes |
|---|---|---|---|
| where | string | yes | City or town, with state or country when ambiguous: 'Lisbon', 'Wimberley, TX', 'Kyoto, Japan'. |
| checkIn | string | yes | YYYY-MM-DD |
| checkOut | string | yes | YYYY-MM-DD, 1 to 90 nights after checkIn (Booking.com is skipped past 30 nights; Vrbo quotes longer stays) |
| adults | integer | no | — |
| children | integer | no | — |
| budget | string | no | value = cheapest that passes, mid = balanced, splurge = the nicest |
| maxTotalUsd | number | no | Hard cap on the whole-stay total in US dollars |
| walkTo | array | no | What should be within a ten-minute walk |
| nearLandmark | string | no | A place the traveller wants to be near: 'Zilker Park', 'the old town', 'Shinkansen station' |
| quietStreet | boolean | no | — |
| pets | boolean | no | A pet is coming: only listings whose own policy allows pets |
| hotelBrands | array | no | Hotel loyalty: keep hotel picks inside these groups (marriott, hilton, hyatt, ihg, accor, wyndham, choice, bestwestern); whole homes are unaffected |
| vibe | string | no | — |
| intent | string | no | What the trip is for, in the traveller's words: 'kayaking', 'a cooking class', 'a quiet writing week'. Steers things to do, never the ranking. |
| stayType | string | no | entire = whole apartments and houses (default); hotel = hotel rooms (Booking.com and Expedia); any = rentals and hotel rooms side by side, each tagged; resort = resorts and all-inclusives, Booking.com |
| flexDays | no | Date flexibility for the alert watcher: 0, 1, 2, 3 or 7 days | |
| travellerCountry | string | no | ISO-2 country the traveller lives in (default US); decides whether an eSIM line applies |
| waitSeconds | integer | no | How long to wait for the search before returning a running status |
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_…).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| searchId | string | yes | The searchId from search_stays, or the id in a stayotter.com/stay/s_… link |
| travellerCountry | string | no | — |
Instant and free: the latest finished standard search for one of the covered cities (a two-adult stay about a month out, refreshed daily). Covered: Austin, Lisbon, Kyoto, Mexico City, New York, Paris, Barcelona, Montreal, San Diego, Edinburgh, Honolulu, London, South Lake Tahoe, Sedona, Holbox, Niagara-on-the-Lake, Bentonville, Knoxville, Asheville, Canmore, Coeur d'Alene, Broken Bow, Lancaster, A
| Parameter | Type | Required | Notes |
|---|---|---|---|
| city | string | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| searchId | string | yes | — |
| intent | string | no | Override: 'kayaking', 'food tour' |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| searchId | string | yes | — |
Reads one place the traveller 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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | A property page URL, or a hotel's name with its city after a comma: 'Hilton Austin, Austin' |
| city | string | no | — |
| checkIn | string | no | YYYY-MM-DD; with checkOut, prices are read too |
| checkOut | string | no | — |
| adults | integer | no | — |
| spot | string | no | A place they will walk to: 'Rainey Street', 'the convention centre' |
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 da
| Parameter | Type | Required | Notes |
|---|---|---|---|
| confirmation | string | yes | The confirmation email's text, as the traveller pasted or forwarded it |
| paidUsd | number | no | What they paid in US dollars, when the confirmation is in a currency the otter can't convert |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Stay Otter or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.3.1 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest1b393b2d678065a914ce0fc73b19360968f9053e1123d80e9156eff126a1adb3
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_stays | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_stay | no tags | |
| city_picks | no tags | |
| get_activities | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| set_alert | state-write | state-write: declares readOnlyHint: false |
| check_listing | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| watch_booking | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest1b393b2d678065a9
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.3.1.
1.3.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Stay Otter can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.