Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Kismet 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
15
tools declared
remote
at its publisher
—
calls last 7d
What it does
Semantic hotel search with real-time availability and price comparison for Kismet Travel
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http kismet-mcp https://mcp.kismet.travel/mcp
# 2 — ask your agent for something these tools do
# list_collections, get_guest_profile, sign_in and 12 more
Kismet costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
KIAll 1 server
kismet1 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 kismet-mcp https://mcp.kismet.travel/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
15 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.
Search the Kismet network for vacation-rental collections (property managers). Returns ranked collections with their slug (collection_id), regions, property count, and supported tools. Use this when the guest asks which managers operate in a place or wants to choose a manager. It is not required before network-wide search: search_bookables and discover_collections span every collection when `col
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free-text search across name, region, and description. |
| region | string | no | Filter by region, state, or country (e.g. "Oregon"). |
| category | string | no | Filter by category, e.g. "vacation_rental". |
| limit | number | no | Max results (default 20). |
Get the signed-in user / guest Kismet account profile, identity, preferences, and account-level signals. Returns the currently authenticated user's (the logged-in guest's) Kismet profile: identity (first name), contact-channel status (whether an email / phone is on file and verified — never the raw values), account-level signals (linked property managers and collections the user has transacted wit
No parameter schema on file.
Trigger the Kismet OAuth sign-in flow for the current guest. Call this whenever the user explicitly asks to sign in, log in, authenticate, or connect their Kismet account — common queries: "sign me in", "log me in", "log me into Kismet", "sign me into Kismet", "connect my Kismet account", "authenticate me", "I want to log in". The host will open its OAuth WebView and run the standard PKCE handshak
No parameter schema on file.
Load READ-ONLY context from a Kismet guest token — e.g. a "continue in your AI assistant" link a property manager handed the guest. Returns the manager and the draft/considered itinerary the token carries (plus any current offer, when one applies), so you can have an informed conversation. This is CONTEXT ONLY: it grants NO account access and is never required for browsing. To actually claim an of
| Parameter | Type | Required | Notes |
|---|---|---|---|
| token | string | yes | The Kismet guest token, OR the "continue in your AI assistant" handoff link that carries it (e.g. https://kismet.travel/continue?kgt=…). Pass the pasted link verbatim — the token is extracted from it; |
Record and verify the email inbox that belongs to THIS agent (not to the person it acts for), so the agent can later sign back in on its own with sign_in_agent. Two steps with the same call: without code, Kismet mails a six-digit code to the address; with code, the inbox is marked verified. Requires the agent bearer from the device flow or a connector sign-in. An agent address is never used to
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | The agent's own inbox address. | |
| code | string | no | The six-digit code from the mail Kismet sent; omit on the first call. |
Sign this agent back in through its own verified email inbox, with no bearer and no action from the person. Two steps with the same call: without code, Kismet mails a six-digit code to the inbox; with code, Kismet returns the agent bearer (access and refresh token) that acts for the linked person. Only a verified inbox on an agent the person already linked works; anything else is told to link
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | The agent's own verified inbox address. | |
| code | string | no | The six-digit code from the mail Kismet sent; omit on the first call. |
Returns a booking link for a specific vacation rental property. Use when a guest is ready to book. When dates are provided they are validated against the property's booking rules (availability, minimum/maximum stay, arrival/departure restrictions); if the stay is not bookable, the result carries datesRejected with the reason and up to three alternate date windows — offer those to the guest instead
| Parameter | Type | Required | Notes |
|---|---|---|---|
| guests | number | no | Number of guests |
| checkIn | string | no | Check-in date (YYYY-MM-DD) |
| checkOut | string | no | Check-out date (YYYY-MM-DD) |
| propertySlug | string | yes | Slug of the vacation rental |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
Primary search tool — use this whenever the guest specifies ANY filter: location, dates, budget, bedrooms, pets, or persona. Returns a ranked list of candidate properties as plain text with each property's slug, name, location, dated or anchor pricing, top personas/features, and tagline — formatted so the LLM can read and reason over them directly. After picking your top candidates from the return
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort | string | no | Sort order. Default "relevance". |
| neLat | number | no | BOUNDS MODE: Northeast latitude |
| neLng | number | no | BOUNDS MODE: Northeast longitude |
| swLat | number | no | BOUNDS MODE: Southwest latitude |
| swLng | number | no | BOUNDS MODE: Southwest longitude |
| guests | number | no | Number of guests |
| offset | number | no | Pagination offset. Default 0. |
| region | array | no | Filter by state/region (e.g., ["Vermont"]). Case-insensitive. |
| sleeps | number | no | Minimum sleeping capacity |
| country | string | no | Filter by ISO alpha-2 country code (e.g., "US") |
| feature | string | no | Soft ranking signal — boost properties with a guest-confirmed feature (e.g., "mountain_views", "spotless_clean", "hot_tub", "cozy", "beachfront"). Does NOT hard-filter. |
| nearLat | number | no | POINT MODE: Latitude to search near |
| nearLng | number | no | POINT MODE: Longitude |
| persona | string | no | Soft ranking signal — boost properties popular with a guest persona (e.g., "hiking", "romantic", "young_family", "pet_owners", "fishing", "luxury"). Does NOT hard-filter. |
| bedrooms | number | no | Minimum bedrooms needed |
| locality | array | no | Filter by city/town name (e.g., ["Stowe"], ["Seaside", "Cannon Beach"]). Case-insensitive. |
| nearUnit | string | no | Default "miles". |
| nearRadius | number | no | POINT MODE: Max distance. Default 25. |
| dateWindows | array | no | Up to 5 date windows to check availability and pricing across. Each window returns per-property availability. Omit for browse mode — browse results carry the nightly anchor "from" price only, never a |
| petsRequired | boolean | no | Pet-friendly only |
Visually discover bookable-stay managers (collections) and their properties as an interactive carousel. OMIT collections to discover across the whole network (the widget shows manager filter cards plus an interleaved property carousel), pass one to feature a single manager, or several to compare. Each property card opens full details. Use this for browsing/visual presentation; use search_bookabl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| neLat | number | no | BOUNDS MODE: Northeast corner latitude. Required with swLat. |
| neLng | number | no | BOUNDS MODE: Northeast corner longitude. Required with swLat. |
| swLat | number | no | BOUNDS MODE: Southwest corner latitude. Use bounding box for geographic regions like coastlines, mountain ranges, lake shores, or any area that is not a single point. Example: Oregon coast → swLat=42. |
| swLng | number | no | BOUNDS MODE: Southwest corner longitude. Required with swLat. |
| guests | number | no | Number of guests |
| offset | number | no | Skip this many results (for pagination / load-more). Default 0. |
| region | array | no | Filter by state or region name (e.g., ["Vermont"], ["Vermont", "New Hampshire"]). Case-insensitive. Use this instead of bounding box when a guest asks for a specific state. |
| sleeps | number | no | Minimum sleeping capacity required (filters properties that sleep at least this many) |
| checkIn | string | no | Check-in date (YYYY-MM-DD) |
| country | string | no | Filter by ISO 3166-1 alpha-2 country code (e.g., "US"). Rarely needed since collections are typically in one country. |
| feature | string | no | Soft ranking signal — boost properties with a guest-confirmed feature. Does NOT hard-filter. Example values: "mountain_views", "spotless_clean", "amazing_host", "cozy", "beachfront", "stocked_kitchen" |
| nearLat | number | no | POINT MODE: Latitude to search near (e.g. 35.789). Use for specific places like a town, address, or landmark. Resolve place names to coordinates before calling. For broad areas (coastlines, mountain r |
| nearLng | number | no | POINT MODE: Longitude to search near (e.g. -83.534). Required when nearLat is provided. |
| persona | string | no | Soft ranking signal — boost properties popular with a guest persona. Does NOT hard-filter. Example values: "hiking", "young_family", "romantic", "pet_owners", "fishing", "honeymoon", "luxury", "foodie |
| bedrooms | number | no | Minimum bedrooms needed |
| checkOut | string | no | Check-out date (YYYY-MM-DD) |
| locality | array | no | Filter by city or town name (e.g., ["Stowe"], ["Seaside", "Cannon Beach"]). Case-insensitive. Use instead of geo when a guest asks for a specific town. |
| nearUnit | string | no | Unit for nearRadius and distance values. Default "miles". |
| nearRadius | number | no | POINT MODE: Max distance from the nearLat/nearLng point in nearUnit. Default 25 miles. Use 50+ for broad areas. |
| preferences | string | no | Free text preferences (e.g., "hot tub, mountain view") |
Present a curated set of specific properties as an interactive visual carousel. Pass propertySlugs in your chosen order, plus the collection_id(s) those properties belong to in collections — you get each candidate's collectionSlug from search_bookables. The picks MAY span multiple managers: pass ALL their collection_ids and the carousel renders them together with manager filter cards. Never fa
| Parameter | Type | Required | Notes |
|---|---|---|---|
| guests | number | no | Number of guests |
| checkIn | string | no | Check-in date for live pricing |
| context | string | no | Optional: the guest's needs/criteria behind these picks (e.g., "Best options for a family of 6 with dogs in Vermont"). Used by the backend as a search/personalization hint — recorded on the guest's jo |
| checkOut | string | no | Check-out date for live pricing |
| propertySlugs | array | yes | Ordered array of property slugs to present. The carousel preserves this order. Max 10. |
| semanticFilters | object | no | Reserved optional evidence-backed semantic criteria that complement the explicit location, date, capacity, pet, property-type, and budget filters. Put true must-haves in required; put preferences th |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
Save or remove a vacation rental property from the guest's shortlist. Reversible. Anonymous guests are tracked via the MCP session ID; signed-in guests via their guest ID — the tool reads the current identity from session context, so no auth fields need to be passed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | Whether to save or remove the property from the shortlist. Optional — defaults to 'save'; pass 'remove' to take a property off the shortlist. |
| checkIn | string | no | Check-in date (ISO 8601). |
| checkOut | string | no | Check-out date (ISO 8601). |
| quoteToken | string | no | Quote token for the selected rate. |
| propertyName | string | no | Display name of the property. Strongly recommended (you have it from search_bookables); if omitted, a readable name is derived from the slug. |
| propertySlug | string | yes | Slug of the property being shortlisted (required). |
| collectionSlug | string | no | Optional. The parent collection slug. If omitted it is derived from the globally-unique propertySlug, so you can save with propertySlug alone. |
| pricingSnapshot | object | no | Pricing snapshot at the time of shortlisting. |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
Get guest reviews for a specific vacation rental property or for the entire collection. Returns a summary and individual review texts that can be used to answer questions about guest experiences.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort | string | no | How to sort reviews (default newest). |
| limit | number | no | Number of reviews to return (default 5, max 20). |
| offset | number | no | Number of reviews to skip for pagination (default 0). |
| season | string | no | Filter to reviews from a specific season. |
| persona | string | no | Filter to reviews from a guest persona type (e.g. "family", "couples", "solo"). |
| propertySlug | string | no | Slug of the specific property to get reviews for. If omitted, returns collection-level reviews. |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
Show the guest's saved/shortlisted vacation rental properties for this collection. Call this when the user wants to see their saved properties or review their shortlist.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Maximum number of saved properties to return (default 20). |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
Returns collection-level content for a VRM. Sections: "about" (collection info), "reviews" (guest reviews with ratings). Use for guest questions about the company, area, or review quality.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max items for reviews. Default 10. |
| offset | number | no | Pagination offset |
| section | string | yes | Content section |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
Returns full details for a specific vacation rental property: description, bedrooms, bathrooms, kitchen, outdoor spaces, features, policies, and recent reviews. Use when a guest wants to know more about a specific property.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| checkIn | string | no | Check-in date for pricing |
| checkOut | string | no | Check-out date for pricing |
| propertySlug | string | yes | Slug of the vacation rental property |
| collections | array | no | Collection slug(s) — each a collection_id from list_collections. For search_bookables and discover_collections: OMIT to span the whole network, pass one to scope to a single manager, or several to c |
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 Kismet 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 0.0.0 · scanned 20 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 · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestd888775e6baa8ed14e0949de8f422506e177d2dc42dafa0eab7c1e6d7daafe0f
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 |
|---|---|---|
| list_collections | no tags | |
| get_guest_profile | no tags | |
| sign_in | state-write | state-write: declares readOnlyHint: false |
| use_guest_token | no tags | |
| verify_agent_inbox | state-write | state-write: declares readOnlyHint: false |
| sign_in_agent | state-write | state-write: declares readOnlyHint: false |
| get_booking_link | state-write | state-write: declares readOnlyHint: false |
| search_bookables | no tags | |
| discover_collections | state-write | state-write: declares readOnlyHint: false |
| build_bookable_carousel | state-write | state-write: declares readOnlyHint: false |
| shortlist_bookable | state-write | state-write: declares readOnlyHint: false |
| get_bookable_reviews | no tags | |
| get_shortlist | no tags | |
| get_collection_content | no tags | |
| get_bookable_detail | no tags |
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestd888775e6baa8ed1
Scanned2026-10-20
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 0.0.0.
0.0.0
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 Kismet 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.