Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
HotelRunner MCP by usefulapi 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
8
tools declared
remote
at its publisher
—
calls last 7d
What it does
Read HotelRunner reservations, rooms, channels; update availability and prices; confirm or cancel.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http hotelrunner-mcp-by-usefulapi https://hotelrunner.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# hotelrunner_list_rooms, hotelrunner_list_reservations, hotelrunner_get_reservation and 5 more
HotelRunner MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 578 servers
usefulapi578 servers
25 categories
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 hotelrunner-mcp-by-usefulapi https://hotelrunner.usefulapi.io/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 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
8 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.
List the property's room types and rates with their inv_code and rate_code, capacity, pricing type, sales currency, connected channel codes and whether availability, restrictions and prices can be updated through the API. Use the inv_code with hotelrunner_update_room_calendar. Counts as one of the property's 250 requests per day (5 per minute). GET /api/v2/apps/rooms.
No parameter schema on file.
List reservations of the property (new, modified, canceled), newest data first as HotelRunner returns them, 1-50 per page. By default ALL reservations created in the window are returned (this tool sets undelivered=false, so reading does not depend on a PMS having fetched them). from_date is the creation date (HotelRunner keeps at most 30 days back; default 10 days); from_last_update_date finds res
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from_date | string | no | Only reservations created on/after this date, yyyy-mm-dd (max 30 days back; default 10 days back). |
| from_last_update_date | string | no | Only reservations updated on/after this date, yyyy-mm-dd. |
| booked | boolean | no | true = only new (not modified) bookings. |
| modified | boolean | no | true = only modified reservations. |
| page | integer | no | Page number, from 1 (default 1). Pass the previous reply's next_page. |
| per_page | integer | no | Reservations per page, 1-50 (default 10). |
| detail | string | no | 'summary' (default) or 'full' vendor records (large). |
One reservation by its HotelRunner code (hr_number, e.g. R377873409) or the sales channel's own reservation code, with the full vendor record (rooms, daily prices, extras, payments, guest and billing details, next_states). If the reservation is older than HotelRunner's lookup window, pass from_date. Counts as one of the property's 250 requests per day (5 per minute). GET /api/v2/apps/reservations?
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reservation_number | string | yes | HotelRunner reservation code (hr_number, e.g. R377873409) or the sales channel's reservation code. |
| from_date | string | no | Creation-date window start, yyyy-mm-dd (HotelRunner keeps at most 30 days back). |
All sales channels HotelRunner supports (name and code, e.g. bookingcom, expedia, hrs, online). The code is what hotelrunner_update_room_calendar takes in channel_codes. Counts as one of the property's 250 requests per day (5 per minute). GET /api/v2/apps/infos/channels.
No parameter schema on file.
The channels this property is connected to, each with counts of calendar update processes in progress, succeeded and failed. Counts as one of the property's 250 requests per day (5 per minute). GET /api/v2/apps/infos/connected_channels.
No parameter schema on file.
Per-channel status of a calendar update: pass the transaction_id returned by hotelrunner_update_room_calendar. Shows succeeded / failed / in-progress counts and each channel's state and error message. Counts as one of the property's 250 requests per day (5 per minute). GET /api/v2/apps/infos/transaction_details.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| transaction_id | string | yes | transaction_id from an update reply. |
WRITE: change availability, price, minimum/maximum stay, stop-sale, closed-to-arrival (cta) or closed-to-departure (ctd) for ONE room type (inv_code) over a date range of at most 90 days, optionally only on some weekdays and only on some channels. Only the fields you pass are changed. This is LIVE inventory: HotelRunner pushes it to every connected channel (Booking.com, Expedia, your own booking e
| Parameter | Type | Required | Notes |
|---|---|---|---|
| inv_code | string | yes | An inventory code from hotelrunner_list_rooms, e.g. HR:1903. |
| start_date | string | yes | First date to change, yyyy-mm-dd. |
| end_date | string | yes | Last date to change (inclusive), yyyy-mm-dd. |
| availability | integer | no | Rooms available to sell. |
| price | number | no | Base nightly price in the property's sales currency. |
| min_stay | integer | no | Minimum nights. |
| max_stay | integer | no | Maximum nights. |
| stop_sale | boolean | no | true = close the room for sale on these dates, false = reopen. |
| cta | boolean | no | Closed to arrival. |
| ctd | boolean | no | Closed to departure. |
| days | array | no | Only these weekdays, 0 = Sunday ... 6 = Saturday (default: every day). |
| channel_codes | array | no | Only these channels (codes from hotelrunner_list_connected_channels); default: all connected channels of the room. |
WRITE: move ONE reservation to the next state: event 'confirm' (hotelier accepts it) or 'cancel' (cancels it; cancel_reason is required: customer, no_room, no_show or invalid_price). Cancel is not reversible through this API and releases the room; HotelRunner may notify the guest or the sales channel (Booking.com, Expedia, ...), so only cancel when the user clearly asked for it, and pass confirm=t
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hr_number | string | yes | HotelRunner reservation code (hr_number). |
| event | string | yes | 'confirm' or 'cancel'. |
| cancel_reason | string | no | Required for cancel: customer, no_room, no_show or invalid_price. |
| confirm | boolean | no | Required true for event 'cancel': the user explicitly approved cancelling this reservation (not reversible). |
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 HotelRunner MCP by usefulapi 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 1.14.3 · scanned 6 Nov 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 digest8d05e76013a4313716e5289513f2da98ff9027209e5e07e52f8e1f3445c9fadf
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 |
|---|---|---|
| hotelrunner_list_rooms | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hotelrunner_list_reservations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hotelrunner_get_reservation | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hotelrunner_list_channels | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hotelrunner_list_connected_channels | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hotelrunner_get_transaction_details | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hotelrunner_update_room_calendar | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| hotelrunner_update_reservation_state | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, 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 digest8d05e76013a43137
Scanned2026-11-06
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 1.14.3.
1.14.3
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 HotelRunner MCP by usefulapi 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.