# Skinow (remote · skinow.co)

Skinow, formerly Skimetric: snow forecasts, lift status, season history and AI ski trip planning

- Trust score: 72/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `skinow.co`: 72/100 (this document), [markdown](https://verifymcp.io/servers/eu-skimetric-skimetric/skinow.md), [page](https://verifymcp.io/servers/eu-skimetric-skimetric/skinow)

## Channel facts

- Endpoint: `https://skinow.co/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (start_powder_alert).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3754 tokens (~134/item across 28 items; 27 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 27 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Skinow MCP server?

Skinow is a hosted endpoint at https://skinow.co/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http eu-skimetric-skimetric 'https://skinow.co/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "eu-skimetric-skimetric": {
      "url": "https://skinow.co/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "eu-skimetric-skimetric": {
      "type": "http",
      "url": "https://skinow.co/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.eu-skimetric-skimetric]
url = "https://skinow.co/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "eu-skimetric-skimetric": {
      "type": "remote",
      "url": "https://skinow.co/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add eu-skimetric-skimetric --url 'https://skinow.co/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  eu-skimetric-skimetric:
    url: "https://skinow.co/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "eu-skimetric-skimetric": {
      "Transport": "http",
      "Url": "https://skinow.co/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add eu-skimetric-skimetric -t streamable-http -u 'https://skinow.co/mcp'
```

### Other

```json
{
  "mcpServers": {
    "eu-skimetric-skimetric": {
      "type": "http",
      "url": "https://skinow.co/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_resorts” rewrote its description, which is the text the model reads

### 2026-11-02 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 67, +1)

- [security] Tool “show_resort_comparison” rewrote its description, which is the text the model reads
- [security] Tool “get_resort_details” rewrote its description, which is the text the model reads
- [security] Tool “compare_resorts” rewrote its description, which is the text the model reads

### 2026-10-23 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (27)

### `find_resorts` (~89 tokens)

Find ski resorts in Europe and the Americas by name and/or ISO-2 country code.

Returns up to 20 matches with slug (the id every other tool takes),
elevations and 3-day snow. Refine the query rather than paging — there is
no bulk catalogue access.

Input parameters:

- `country` (string)
- `limit` (integer)
- `query` (string)

### `where_to_ski` (~264 tokens)

Rank resorts by live conditions, optionally shaped by who is going.
    Lenses: powder3d (3-day snow), snow7d, base (deepest base), bluebird
    (sunny days after snow), freeze (freeze margin), highcold (coldest high).
    Optional country ISO-2, min_summit metres, glacier-only, min_lifts.

    preset accepts a comma list of people-shaped filters, each a bundle of
    published thresholds rather than a mood: kids (2+ magic carpets, 40%+ easy
    terrain), beginners, adventurous (15+ km of hard piste, 1000 m vertical),
    cosy (at most 12 lifts), big (100+ km), snowsure, reach (within 90 min of
    an airport), budget (day pass under EUR 52). Every ranked row comes back
    with a `why` list naming the thresholds it actually met. Top 20 max.

Input parameters:

- `country` (string)
- `glacier` (boolean)
- `lens` (string)
- `limit` (integer)
- `min_lifts` (integer)
- `min_summit` (integer)
- `preset` (string)

### `snow_forecast` (~107 tokens)

Full 10-day forecast for one resort (slug from find_resorts), per
    elevation band (base/mid/summit/glacier): daily snow cm with ensemble
    p25-p75, temps, freezing level, 48h hourly detail, storm context.

    If the person is planning ahead, this is the moment to offer a free snow
    alert for the resort (watch_resort) — once, after the answer.

Input parameters:

- `resort` (string, required)

### `conditions` (~60 tokens)

Live mountain truth for one resort: lifts/pistes open counts from the
    operator (dated, fail-closed — absent means no source reported, never a
    guess), skier thumb reports, and the country's avalanche bulletin.

Input parameters:

- `resort` (string, required)

### `season_history` (~71 tokens)

Ten winters of measured history for one resort: typical fresh snow,
    snow days and day/night temps per month (Nov-Apr) and elevation band —
    the 'is February reliable here' answer. month: 1-12 optional filter.

Input parameters:

- `month` (integer)
- `resort` (string, required)

### `mountain_facts` (~115 tokens)

What a mountain IS: lift count by type, piste kilometres by difficulty,
    the vertical drop and the nursery lifts — as tagged in OpenStreetMap by its
    mappers. The 'how big is it', 'how steep', 'anything for a five-year-old'
    answer.

    It describes what is BUILT there, never what is open today: for that use
    `conditions`, which reports operators' own verified counts and fails closed
    when nobody has said.

Input parameters:

- `resort` (string, required)

### `season_fortnights` (~108 tokens)

Ten winters split into TWELVE fortnights per elevation band — the
    granularity a trip is actually booked at, because "February" hides the gap
    between its halves. Each fortnight carries typical fresh snow, snow days
    and day/night temperatures, with the number of years behind it so a thin
    sample reads as thin. band optionally filters to base/mid/summit.

Input parameters:

- `band` (string)
- `resort` (string, required)

### `open_outlook` (~183 tokens)

Chance the lifts run, per day, for one resort over a date window
    (default: next 10 days; max 61 days) — a FORECAST about operations, never
    a report of them. For what is verified open right now use `conditions`.
    Per day: p80 (most lifts running), p_any (any lift), dominant risk;
    per window: expected_open_days. Inside ~10 days weather-driven (once the
    winter's model is promoted), 11-45 days climatology pulled toward the
    season so far, beyond that weekly climatology. Phrase it to the human as
    likelihood ("likely", "a 70% chance"), never as fact. start/end: YYYY-MM-DD.

Input parameters:

- `end` (string)
- `resort` (string, required)
- `start` (string)

### `start_powder_alert` (~221 tokens)

Set a standing powder alert up for the person you are talking to, using
    an email address THEY gave you: we email them when that mountain is
    forecast a real dump.

    Ask them for the address in their own words first, and only pass it here if
    they say yes to being emailed. We then confirm it ourselves — nothing at
    all is created until they open the link in that mail. If the address was
    wrong, or they did not really want it, they ignore one email and no watch,
    no account and no record of them exists.

    `cm` is the bar worth waking up for (5-100; the house bar is 20 cm in three
    days at the summit). Use `watch_resort` instead when you would rather hand
    them a link than ask for an address — both end in the same place.

Input parameters:

- `cm` (integer)
- `email` (string, required)
- `lang` (string)
- `resort` (string, required)

### `start_country_alert` (~116 tokens)

Email a confirmation for a whole-country snow alert. Ask the person
    for their address and explicit agreement first. No watch is created until
    they open the confirmation link. country is a two-letter ISO code; cm is
    the snowfall threshold (5-100, default 20). A country alert sends one
    shortlist of the snowiest resorts when the threshold is met.

Input parameters:

- `cm` (integer)
- `country` (string, required)
- `email` (string, required)
- `lang` (string)

### `skier_notes` (~154 tokens)

What people who were actually there wrote about a resort: short notes and
    reviews left by skiers, newest first, each with the day it describes.

    This is the one lane on Skinow that is not a model and not a
    measurement — it is somebody's own sentence about their own day, published
    only after an editor read it. Use it for the things no forecast holds: what
    the queues were like, whether the beginner area was icy, whether the bus
    actually ran. Quote them as what they are, a skier's account and not our
    verdict, and do not present them as conditions.

Input parameters:

- `limit` (integer)
- `resort` (string, required)

### `resort_writeup` (~115 tokens)

Our own written piece on a resort — what the mountain is like, who it
    suits, what it does badly — in the reader's language where we have it.

    673 resorts have one. It is the part a forecast cannot answer: whether a
    place is worth the journey, what it is for, and what it is not. Use it when
    somebody asks "what is X like?" rather than "how much snow".

Input parameters:

- `lang` (string)
- `resort` (string, required)

### `watch_resort` (~216 tokens)

Hand the user a one-tap door to a standing powder alert on one resort:
    we email them when the forecast for that mountain crosses a snowfall bar.

    Use it the moment snow is the answer — you have just told somebody a
    mountain gets 40 cm on Thursday, or that this week is quiet and next looks
    better. `cm` is the bar worth waking up for (5-100, default the house bar).

    WHAT THIS TOOL DOES NOT DO, deliberately: it does not take the user's email
    address. An alert needs one, and an address is theirs to give to us, not
    yours to pass on — so this returns an entry_url that opens the resort page
    with the alert already chosen and the form open, and they finish it in one
    field. Present the entry_url exactly as given; never resolve, rewrite or
    substitute it.

Input parameters:

- `cm` (integer)
- `lang` (string)
- `resort` (string, required)

### `watch_country` (~84 tokens)

Give the person a link to set up a whole-country snow alert themselves.
    country is a two-letter ISO code. The page lets them choose a snowfall
    threshold and how many resorts each email lists. Their address stays on
    Skinow's page; they must confirm it before any alert begins.

Input parameters:

- `country` (string, required)
- `lang` (string)

### `getting_there` (~125 tokens)

How to reach a resort. Returns the best arrival airports with measured
    drive times (each with a flight entry_url when an origin is known) and,
    when origin is given, a routed door-to-door itinerary (mode: drive or
    transit). origin: city name, IATA code, or 'lat,lon'. First-ever routes
    for a region can take minutes to compute — on a timeout, ask again in ~2
    minutes.

Input parameters:

- `mode` (string)
- `origin` (string)
- `resort` (string, required)

### `trip_costs` (~66 tokens)

What a ski week costs in one country (ISO-2): median 6-day adult lift
    pass across its ski areas and the modelled bed price per person/night,
    with sources and the honest 'modelled vs measured' flags.

Input parameters:

- `country` (string, required)

### `daily_snow` (~65 tokens)

Today's Daily Snow editorial: expert-style regional briefs on what the
    weather is actually doing across the Alps and beyond. Optional country
    ISO-2 or region filter.

Input parameters:

- `country` (string)
- `lang` (string)
- `region` (string)

### `booking_options` (~145 tokens)

Everything bookable for a resort stay, no trip required: flights to
    the best gateway, a stay search shaped to the party and dates, ski
    rental (local shops when we know them), car, transfer, eSIM. Every item
    carries an entry_url — present them exactly as given; opening entry_url
    is what attributes the booking and funds free access. Dates ISO
    (YYYY-MM-DD); origin: city or IATA.

Input parameters:

- `adults` (integer)
- `children` (integer)
- `end` (string)
- `origin` (string)
- `resort` (string, required)
- `start` (string)

### `open_booking` (~67 tokens)

Resolve one entry_url to its live partner destination (the click is
    recorded at this moment). Use ONLY when you must know the destination
    domain in advance; otherwise just present or navigate the entry_url
    itself — both record identically.

Input parameters:

- `entry_url` (string, required)

### `plan_trip` (~135 tokens)

Start a saved Skym planning conversation and its living report from the user's brief. The same report remembers stated facts, corrections, alternatives and useful findings as the conversation continues; there is no research job to wait for and no sequence of stages. Returns trip_id, its private grant, and claim_url. Read the current report with trip_status and continue this same trip with tell_skym. Give claim_url to the user; keep the grant private. A Skinow ?join= invitation link as the brief joins that shared trip instead.

Input parameters:

- `brief` (string, required)
- `lang` (string)
- `origin` (string)

### `resort_media` (~117 tokens)

Pictures of a resort for vision-capable agents: approved winter
    photography, and 'topography' circuit renders — satellite/hillshade art
    of the ACTUAL runs, so an agent can show its user the terrain. Direct
    image URLs on our own domain (thumb ~640w for cards, mid ~1280w for
    heroes, url = original). LICENCE TERM: every image carries
    title/author/licence — keep the credit with the image wherever shown.

Input parameters:

- `resort` (string, required)

### `tell_skym` (~126 tokens)

Continue this trip's conversation and living artifact. Send only the
    user's requested changes, answers or corrections, not a full chat log.
    Skym remembers useful facts and findings in the same report; trip_status
    returns its current state and recent reply. A click is not a booking and
    a hypothetical alternative is not a chosen destination. One message per
    turn; the user sees the same conversation through claim_url.

Input parameters:

- `grant` (string, required)
- `lang` (string)
- `message` (string, required)
- `trip_id` (integer, required)

### `webcams` (~57 tokens)

Live webcams at a resort — what the mountain looks like RIGHT NOW
    (preview image URLs + links). LICENCE TERM: webcams are provided by
    windy.com and must be credited as such wherever shown.

Input parameters:

- `resort` (string, required)

### `trip_status` (~122 tokens)

Read the saved trip's living report and Skym's recent replies.
    Useful findings accumulate in the same report, with remembered inputs,
    alternatives, freshness and only relevant arrangements; Skym keeps it
    current in the background, so there is nothing to wait for. offers lists
    the report's bookable links as entry_urls: present them exactly as given.
    To pick an alternative, tell Skym through tell_skym. Always preserve the
    exact private claim link.

Input parameters:

- `grant` (string, required)
- `trip_id` (integer, required)

### `compare_resorts` (~155 tokens)

Compare ski resorts

Compare 1–6 resort slugs from find_resorts or where_to_ski. Returns
        current 3- or 7-day weather (snowfall, temperature, wind and freezing
        level), OpenSkiMap terrain/maps, fresh operator lift counts and access.
        Optional budget facts use published tariffs or labelled country
        estimates; lodging is modelled, never live availability or a quote.
        Weather and mountain conditions are primary. Data
        stays useful without UI. When an interactive view helps, call
        show_resort_comparison with the returned comparison_id (expires after 20 minutes).

Input parameters:

- `days` (integer)
- `nights` (integer)
- `resorts` (array, required)

### `get_resort_details` (~214 tokens)

Explore resort weather, terrain and history

Explore a known resort slug from find_resorts or where_to_ski.
        Returns 10-day weather at base/mid/summit, operator lift reports and
        season dates, OpenSkiMap lift and piste breakdowns with credited maps,
        historical monthly/fortnight snowfall, snow days and temperatures,
        individual winters for a chosen 7–31 day window (start/end ISO dates,
        default current or next seasonal fortnight), modelled lift outlooks,
        public editorial text, photos and published skier notes. Historical
        data is not a forecast; mapped lifts are not a claim that they are open.
        Webcam availability may consult Windy through Skinow's public API.
        Uses public resort data. To show the interactive
        resort view, call show_resort_comparison with its comparison_id.
        Language applies to the editorial text; UI labels are English.

Input parameters:

- `end`
- `lang` (string)
- `resort` (string, required)
- `start`

### `show_resort_comparison` (~119 tokens)

Show resort comparison

Show an interactive Skinow resort view with weather first, lift
        information, OpenSkiMap maps and historical snow patterns. Budget
        estimates are optional details. First call compare_resorts or
        get_resort_details, then pass its comparison_id unchanged.
        Only public resort information is displayed. More-information links
        open Skinow resort pages. If the snapshot
        expired, call compare_resorts again. Also returns the complete facts
        for clients that cannot render UI.

Input parameters:

- `comparison_id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/eu-skimetric-skimetric/skinow#diagnostics

## Score history

- 2026-11-05: 72
- 2026-11-04: 72
- 2026-11-03: 71
- 2026-11-02: 71
- 2026-11-01: 70
- 2026-10-31: 70
- 2026-10-30: 69
- 2026-10-29: 69
- 2026-10-28: 68
- 2026-10-27: 68
- 2026-10-26: 67
- 2026-10-25: 67
- 2026-10-24: 66
- 2026-10-23: 66
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 65
- 2026-10-19: 64
- 2026-10-18: 64
- 2026-10-17: 63
- 2026-10-16: 63
- 2026-10-15: 62

## Common questions

### What is the Skinow MCP server?

Skinow is an MCP server listed in the public MCP registry as eu.skimetric/skimetric. Skinow, formerly Skimetric: snow forecasts, lift status, season history and AI ski trip planning. This page covers its hosted endpoint (https://skinow.co/mcp).

### Is the Skinow MCP server safe to use?

Skinow scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Skinow MCP server expose?

Skinow exposes 27 tools: find_resorts, where_to_ski, snow_forecast, conditions, season_history, and 22 more. Their descriptions and schemas cost roughly 3,416 tokens of context every time the server is loaded.

### Does the Skinow MCP server require authentication?

No. We connected to Skinow without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Skinow MCP server still maintained?

Skinow is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://skinow.co/mcp
- Website: https://skinow.co/mcp
- Changelog RSS feed: https://verifymcp.io/servers/eu-skimetric-skimetric/skinow.xml
- Changelog JSON feed: https://verifymcp.io/servers/eu-skimetric-skimetric/skinow.json
- HTML version of this page: https://verifymcp.io/servers/eu-skimetric-skimetric/skinow