Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
G Guest 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.
96/100
tool-list score
8
tools declared
remote
at its publisher
—
calls last 7d
What it does
Book a table, appointment or class at a real local business. Instant confirmation, no API key.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http g-guest-mcp https://g-guest.app/api/mcp
# 2 — ask your agent for something these tools do
# search, fetch, get_business and 5 more
G Guest costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
GGAll 1 server
g-guest1 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 g-guest-mcp https://g-guest.app/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 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.
Search bookable businesses on G-Guest by name or slug. Returns ids you can pass to fetch or to the booking tools.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
Fetch full details for one business id returned by search: services, hours, timezone and how to book it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Look up a business on G-Guest: services, opening hours, timezone and maximum party size. Call this first if you only know the slug.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Business identifier, e.g. "demo". |
List bookable time slots for a business on a given date and party size. Offer the guest only slots where available is true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| date | string | yes | YYYY-MM-DD, in the venue's local calendar. |
| party_size | integer | yes | — |
Create a real reservation. Use a start value returned by check_availability. Never invent guest details. Ask the person for their real name, email and phone first. If the result status is pending_confirmation, show the guest the confirmation_url. If it is pending_payment, the venue takes a prepayment: show the guest the payment_url, and do not say it is booked until it is paid.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | — |
| start | string | yes | The slot's start value, copied exactly as check_availability returned it. |
| party_size | integer | yes | — |
| name | string | yes | — |
| string | yes | — | |
| phone | string | yes | — |
| notes | string | no | — |
| idempotency_key | string | no | Retry safety: pick any unique string for this booking attempt and reuse it on retries. The same key always returns the same booking, never a duplicate. |
| language | string | no | The guest's language as an ISO 639-1 code: en, nl, de, fr, es, it, id or bg. The confirmation, the reminders and the manage page are sent in it. Defaults to English. |
| source | string | no | Which assistant is booking. Defaults to other_ai. proof_video is our own channel: bookings made while filming a proof clip. |
Look up one existing booking so the guest can confirm when and where it is. Identify it with the booking_id and manage_token that create_booking returned; both also sit in the guest's confirmation email as the manage link, /booking/<booking_id>?token=<manage_token>. Returns the business, the local date and time with its timezone, party size, service and status: confirmed, pending_confirmation, pen
| Parameter | Type | Required | Notes |
|---|---|---|---|
| booking_id | string | yes | The booking_id create_booking returned, or the id in the guest's manage link. |
| manage_token | string | yes | The token from the same booking's manage link. If the guest only has the link, take the token from its ?token= parameter. |
Cancel an upcoming booking and release its slot to other guests. Identified like check_booking: booking_id plus manage_token. Confirm with the guest before calling; the cancellation is immediate and this server cannot undo it, the guest would simply book again. The venue is notified exactly as for a cancellation from the manage link. Safe to retry: cancelling a booking that is already cancelled re
| Parameter | Type | Required | Notes |
|---|---|---|---|
| booking_id | string | yes | The booking_id create_booking returned, or the id in the guest's manage link. |
| manage_token | string | yes | The token from the same booking's manage link (its ?token= parameter). |
Ask G-Guest to list a business that is not on it yet. Use it when the person you are helping runs a restaurant, cafe, bar, salon, spa, studio or clinic and wants reservations that assistants can make. Nothing is published by this call: the request reaches the G-Guest team as a lead, a person reviews it and contacts the business, and only then is anything set up. The owner's or manager's email is r
| Parameter | Type | Required | Notes |
|---|---|---|---|
| business_name | string | yes | The business's own name, as its owner writes it. |
| city | string | yes | City and country, e.g. "Canggu, Indonesia". |
| business_type | string | yes | The closest category. |
| contact_email | string | yes | Email of the owner or manager who asked. The reply goes here. |
| contact_phone | string | no | Phone with country code, optional. |
| contact_name | string | no | Who asked, so the reply can address them by name. |
| website | string | no | The business website or Instagram page, if it has one. |
| message | string | no | Anything the owner wants the team to know: languages, seats, how bookings are taken today. Up to 500 characters. |
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 G Guest 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 96 / 100
Release 1.0.1 · 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 score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest49c58c644d627118872d123be08432f711671116fd786f598755389108c7812a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search | untrusted-input | untrusted-input: keyword "fetch" |
| fetch | untrusted-input | untrusted-input: keyword "fetch" |
| get_business | no tags | |
| check_availability | no tags | |
| create_booking | no tags | |
| check_booking | no tags | |
| cancel_booking | no tags | |
| request_listing | 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 digest49c58c644d627118
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 1.0.1.
1.0.1
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 G Guest 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.