Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Hemmabo 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.
What it does
HemmaBo MCP server for AI-ready direct booking on host-owned vacation-rental domains. AI agents discover host booking pages and verify signed stay offers (VRP · Ed25519/JWKS). HemmaBo is the host-owned trust layer for vacation rentals: every host runs 0%-
Quickstart
Its package declares no executable, so there is no one-line install: it is started the way its own source says, usually as a module rather than a command.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Hemmabo as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Its package declares no executable, so there is no one-line install: it is started the way its own source says, usually as a module rather than a command.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Use this tool when a host is still EVALUATING whether HemmaBo fits; use hemmabo_get_host_onboarding_link only when the host has decided and wants to start. Never call both in the same turn — this tool's next_step already contains the same onboarding URL. Read-only fit check for a vacation-rental…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| propertyName | no | — | |
| propertyType | no | — | |
| country | no | — | |
| region | no | — | |
| city | no | — | |
| domain | no | — | |
| currentChannels | array | no | Optional list of channels the host uses today. Omit when unknown. Helps assess migration fit from OTAs to their own booking website. |
| hasOwnDomain | boolean | no | True if the host already owns a domain or explicitly wants one (e.g. true for 'I have villaakerlyckan.se'). False or omit when still undecided. |
| wantsDirectPayments | boolean | no | True if the host wants Stripe Connect payouts direct to their account. False or omit when they expect HemmaBo to be merchant of record (not supported). |
| wantsAiAgentBooking | boolean | no | True if the host wants AI agents (ChatGPT, Claude, Cursor) to discover and book via their own official website. False or omit when they only want a guest website. |
| preferredLanguage | no | — |
Use this tool only when the host has already decided to start; if the host is still evaluating, use hemmabo_check_host_readiness instead — it returns the same onboarding URL in next_step. Never call both in the same turn. Return a safe HemmaBo onboarding handoff URL for a vacation-rental host who…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| propertyName | no | — | |
| country | no | — | |
| region | no | — | |
| city | no | — | |
| domain | no | — | |
| language | no | — |
Verify that a vacation-rental host domain is a valid Vacation Rental Protocol (VRP) node before trusting it. Reads the domain's .well-known/vacation-rental.json and JWKS. Read-only trust check: no availability, pricing, booking, or payment — do NOT use it to answer those questions. Use when a host…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | yes | — |
Use this tool for the final, host-signed price and booking link for exact dates — the only numbers an agent may quote. For a bare availability yes/no on a propertyId, hemmabo_check_availability is lighter and sufficient. Fetch, verify, and render a live host-domain signed VRP stay offer for exact…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | yes | — | |
| checkIn | string | yes | Requested arrival date in YYYY-MM-DD format (e.g. '2026-11-14'). Must be strictly before checkOut. Use the same dates the guest requested in search. |
| checkOut | string | yes | Requested departure date in YYYY-MM-DD format (e.g. '2026-11-17'). Must be strictly after checkIn. Guest does not stay the departure night. |
| guests | integer | yes | Total guest count as positive integer (e.g. 2, 4). Used by the host node for capacity validation and guest-tier pricing on the signed offer. |
| language | string | no | The guest's conversation language, as a BCP-47 tag (e.g. 'en', 'sv', 'de', 'sv-SE') — ALWAYS pass this, matching the language the guest is chatting in, so the rendered widget's labels, dates and curre |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- 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 Hemmabo or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
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
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
The package declares no program to run, so there is no install command to pin to a release. The history below is for reading; the current release on file is 7.1.0.
- Read-only tools no longer carry a redundant retry hint.
No release note was published with this version.
No release note was published with this version.
No release note was published with this version.
No release note was published with this version.
No release note was published with this version.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
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.
Any signed-in account that does not publish Hemmabo can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.