Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Agent Salon SF 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
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
SF salon prices, add-ons and source-backed comparisons. No live slots or in-tool booking.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agent-salon-sf-mcp https://agentsalonsf.com/mcp
# 2 — ask your agent for something these tools do
# compare_options, search_merchants, check_availability and 7 more
Agent Salon SF costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AGAll 1 server
agentsalonsf1 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 agent-salon-sf-mcp https://agentsalonsf.com/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
10 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.
START HERE for choosing a service under a budget, with extras, or on a date. Use search_merchants for name/address lookup; use this tool for the service decision. Compare a supported service intent, optional budget/date/neighborhood, strict or nearby geography, and selected add-ons (blow_dry, haircut, toner, shampoo, deep_conditioning, iron_finish, extensions). Returns options, uncertain and exclu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| service_intent | string | yes | color, balayage, balayage color, creative color, color consultation, highlights, haircut, mens haircut, womens haircut, wash cut style, or blowout; unsupported intents are errors |
| budget | number | no | USD cap for the requested service and selected/mandatory extras. A lower bound is not proof the full price fits. |
| date | string | no | Valid YYYY-MM-DD in America/Los_Angeles; not a confirmed appointment |
| neighborhood | string | no | — |
| geography | string | no | strict by default; nearby requires a neighborhood and explicit permission to include nearby salons. |
| selected_addons | array | no | Only extras the user requested. Mandatory extras are added automatically; unknown charges are not free. |
| salon | string | no | Optional salon slug or ref from search results to compare only that salon. |
| require_availability | boolean | no | Require provider-confirmed availability. None exists today; opening hours and candidate times cannot satisfy this. |
| limit | integer | no | Total entries across options/uncertain/excluded; continue with next_offset |
| offset | integer | no | — |
Discovery and name/address lookup, not an extras-inclusive price decision. For a supported service with budget, extras or date, start with compare_options. Find San Francisco hair salons and barbers by name/street (q), neighborhood (with nearby), service, date/time and online booking. Returns compact task summaries by default: depth (profiled = researched in depth; listed = public records + the bu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| neighborhood | string | no | Neighborhood slug, label or alias (e.g. "soma", "mission") or an area (e.g. "union-square") |
| service | string | no | Service tag (e.g. "balayage"), intent slug (e.g. "hair-color", "open-saturday", "mens-haircut") or free text |
| day | string | no | Open on this day per published hours: Mo..Su or e.g. "saturday" |
| open_after | string | no | Closes after HH:MM (on day if given) |
| has_booking | boolean | no | Only salons with (true) / without (false) an online booking link |
| q | string | no | Business name or street, fuzzy (e.g. "cinta", "hairshaper", "23 grant") |
| include_nearby | boolean | no | With neighborhood: also include salons within ~400 m (match="nearby", distance_label). Default true. |
| date | string | no | YYYY-MM-DD in the city’s timezone (default today): hours_for_day is computed for this date |
| time_after | string | no | HH:MM — with date: only intervals open after this time count |
| time_before | string | no | HH:MM — with date: only intervals open before this time count |
| open_on_date | boolean | no | Only salons open on date per published hours (not live slots) |
| view | string | no | summary = compact task view (default); full = every field |
| depth | string | no | Only salons of this depth: profiled (booking-system depth), detailed (priced menu + booking link + hours or durations), listed (the rest) |
| haircut_type | string | no | Only salons with an offering of this normalized haircut type (profiled salons) |
| hair_length | string | no | — |
| max_price | number | no | Base offering price in USD, not the complete service with extras; use compare_options for that. Only offerings whose price is KNOWN to be at most this (fixed or bounded range); starting prices do not |
| stylist | string | no | Stylist display name (profiled salons) |
| specialty | string | no | — |
| require_availability | boolean | no | Only offerings with PROVIDER-CONFIRMED start times in the date/after/before window. Schedule-derived candidate start times never satisfy it; salons that have only candidates are returned under `unconf |
| after | string | no | HH:MM earliest start (with date); applied to start times only under require_availability |
Published facts for one salon, NOT live availability and NOT an extras-inclusive quote. For a service/budget/extras/date decision use compare_options with salon=ref. For one salon (ref from search_merchants) and a date: published opening hours on that date (open/closed — NOT live appointment slots), offerings matching the service with published prices and durations, the booking link and step-by-st
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | "<city>/<vertical>/<slug>" |
| date | string | no | YYYY-MM-DD (default today in the city’s timezone) |
| service | string | no | e.g. "balayage", "mens-haircut" or free text |
| time_after | string | no | — |
| time_before | string | no | — |
All published facts for one salon by ref "<city>/<vertical>/<slug>" (from search results), with crawl_log (every source fetched or checked, with time, result and the facts it gave) and last_verified_at: address, phone, hours, licence, registry, services with published prices, booking link, per-field sources (verification), what we verified and what we did not.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | e.g. "san-francisco/hair-salon/hairshaper" |
Salons covered (San Francisco), ordered profiled, detailed, then listed, with depth, neighborhood, price floor and range, stylist count, availability basis and freshness, last_verified_at and verification date. Paginated: limit (default 50, max 200), offset, depth=profiled|detailed|listed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| offset | integer | no | — |
| depth | string | no | profiled = booking-system depth; detailed = priced menu + booking link + hours or durations; listed = the rest |
Base offering lookup by haircut type, length or stylist. Use compare_options for a supported service with budget, extras or date; preserve any unsupported stylist/length/time requirements for merchant confirmation. Find haircut offerings (and optionally stylists and candidate start times) that satisfy ALL given constraints, across profiled salons (hand-normalized menus) and listed salons (type and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| haircut_type | string | no | — |
| hair_length | string | no | — |
| q | string | no | — |
| max_price | number | no | — |
| neighborhood | string | no | — |
| stylist | string | no | — |
| specialty | string | no | — |
| date | string | no | — |
| after | string | no | — |
| before | string | no | — |
| require_availability | boolean | no | — |
| limit | integer | no | — |
Full record for one salon as markdown: facts, hours, every haircut service with price/duration/inclusions, stylists, policies, attributes, evidence, booking rules, candidate start times from the published schedule. Every fact carries a status tag and date.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Salon slug, e.g. "hairshaper" |
| format | string | no | — |
One stylist, under the name the salon's booking system shows: salon, bookable status, specialty evidence with sources, services and prices, candidate start times from the published schedule, and booking link.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Stylist slug, e.g. "hairshaper-shirley", or a display name like "Shirley" |
| format | string | no | — |
NOT live availability. Use compare_options for budget/extras/date decisions. Candidate start times for one offering at one salon, optionally one stylist and a date/time window: candidate start times from the salon's published staff schedule; existing bookings are not subtracted, so some may already be taken — confirm on the booking page. Results carry slotBasis "schedule_candidates" and bookingsSu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| salon | string | yes | — |
| offering | string | yes | Offering id or slug from get_salon |
| stylist | string | no | — |
| date | string | no | Salon-local date |
| after | string | no | — |
| before | string | no | — |
| limit | integer | no | — |
The salon's own booking URL plus exact remaining steps for a given service, stylist, and start time. This site never books on the user's behalf; precision says how much the link pre-selects.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| salon | string | yes | — |
| offering | string | no | — |
| stylist | string | no | — |
| start | string | no | ISO start time from get_availability |
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 Agent Salon SF 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 1.0.0 · scanned 24 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 digestbd3101b896c67f63f7c84ec25cedbd893c77ef43cedd9d28bd7976ab36ba7981
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 |
|---|---|---|
| compare_options | no tags | |
| search_merchants | no tags | |
| check_availability | no tags | |
| get_merchant | untrusted-input | untrusted-input: keyword "crawl" |
| list_salons | no tags | |
| search_haircuts | no tags | |
| get_salon | no tags | |
| get_stylist | no tags | |
| get_availability | no tags | |
| get_booking_link | 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 digestbd3101b896c67f63
Scanned2026-10-24
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 1.0.0.
1.0.0
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 Agent Salon SF 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.