Sealmark
Automated re-test on 2026-11-20: not checked by hand, and not yet reviewed by the maintainers.

Results / snowsure-mcp-server

snowsure-mcp-server

version tested 3.7.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run48 tools

Sealmark's automated test of snowsure-mcp-server 3.7.0 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B and effects A). Tools reached with a valid call: 34 of 48. Of its 6 checks, 5 passed and 1 partial. 3 more checks are advisory, and advisory checks never change a grade: 3 not applicable. The run used Sealmark 1.0.1 with the standard settings.

B

Grade B

The server's grade is its lowest test-area grade. How grading works

Tools reached with a valid call: 34 of 48.

Grade by test area

B
Protocol3.5/4 points
A
Effects2/2 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 48 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server snowsure-mcp 3.7.0 answered; 48 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 48 tool definition(s) and serverInfo, 12 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
partial
0 internals leak(s), 41 invalid call(s) accepted
Evidence for robust-input: first 6 of 41 lines
  1. Probe get_powder_reels: every typed argument has the wrong type
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool get_powder_reels
  2. Probe get_powder_reels: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool get_powder_reels
  3. Probe get_powder_reels: wrong types plus an unexpected extra argument
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool get_powder_reels
  4. Probe get_powder_reels: every string argument is an object
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool get_powder_reels
  5. Probe search_resorts: every typed argument has the wrong type
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool search_resorts
  6. Probe search_resorts: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool search_resorts
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 100 captured response(s), 42 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
n/a
the server sent no instructions
refusal-quality (advisory)
Refusals say what to do next
n/a
no refusal was recorded in this run, so there is nothing to judge

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
pass
get_powder_reels, search_resorts, find_powder_trips, find_resorts_by_criteria, get_southern_hemisphere_report, get_season_openings, get_season_leaderboard, get_elnino_rankings, plan_ski_trip, get_regional_summary, list_insight_categories, get_insights, compare_passes, get_storm_watch declared read-only and changed nothing in the observed directories during a benign call (get_snow_report, get_resort_info, get_resort_photos, find_best_powder, compare_forecasts, get_weather_forecast, get_snow_history, get_monthly_snow, get_elnino_signal, get_webcam_status, list_saved_resorts, list_alerts, get_my_snow_report, get_avalanche, get_snow_quality, get_operating_risk, get_road_access, get_road_cameras, get_road_weather, find_flights_to_powder not judged: the control call failed)
openworld-honesty
Closed-world tools stay on the machine
pass
33 closed-world tool(s) called; nothing connected to the loopback listener (path and git tools cannot be pointed at it, so this confirms only that nothing connected out during the call)
undeclared-writes (advisory)
Unannotated tools leave the sandbox unchanged
n/a
every tool carries annotations, nothing to check

Each check id links to what it tests and how to fix a failure. The same text is in sealmark explain <id>.

Under a check, Evidence shows what it probed (sent or inspected) and what it observed in this run: up to 6 lines per check, each cut at 240 characters, for checks that are not security checks. The text is shortened, and paths and anything that looks like a secret or token are replaced. Run sealmark run --format json yourself for every line in full.

By tool

Which checks called each tool with a valid call in this run, and which did not exercise it. A check can leave a tool out for several reasons: a limit Sealmark sets, a tool left out by design, input the run could not fill in, or a call that returned an error. The CLI report gives the reason. A verdict belongs to the whole check, not to one tool: a failed check that called three tools does not say which one failed. Security checks are left out of this table.

ToolCalled byNot exercised by
ask_snowdataNo check listed here called it with a valid call.None
get_snow_reportNo check listed here called it with a valid call.None
get_powder_reelsNo check listed here called it with a valid call.None
get_resort_infoNo check listed here called it with a valid call.None
get_resort_photosNo check listed here called it with a valid call.None
get_resortNo check listed here called it with a valid call.None
search_resortsNo check listed here called it with a valid call.None
find_best_powderNo check listed here called it with a valid call.None
find_powder_tripsNo check listed here called it with a valid call.None
compare_forecastsNo check listed here called it with a valid call.None
get_weather_forecastNo check listed here called it with a valid call.None
find_resorts_by_criteriaNo check listed here called it with a valid call.None
get_southern_hemisphere_reportNo check listed here called it with a valid call.None
get_season_openingsNo check listed here called it with a valid call.None
get_season_leaderboardNo check listed here called it with a valid call.None
get_snow_historyNo check listed here called it with a valid call.None
get_monthly_snowNo check listed here called it with a valid call.None
get_trip_windowNo check listed here called it with a valid call.None
get_elnino_signalNo check listed here called it with a valid call.None
get_elnino_rankingsNo check listed here called it with a valid call.None
plan_ski_tripNo check listed here called it with a valid call.None
get_webcam_statusNo check listed here called it with a valid call.None
get_regional_summaryNo check listed here called it with a valid call.None
list_insight_categoriesNone
get_insightsNo check listed here called it with a valid call.None
get_ml_trendsNo check listed here called it with a valid call.
get_destinationNo check listed here called it with a valid call.
list_saved_resortsNo check listed here called it with a valid call.
save_resortNo check listed here called it with a valid call.
remove_saved_resortNo check listed here called it with a valid call.
subscribe_alertsNo check listed here called it with a valid call.
list_alertsNo check listed here called it with a valid call.
unsubscribe_alertsNo check listed here called it with a valid call.
book_lodgingNo check listed here called it with a valid call.
get_passNo check listed here called it with a valid call.
find_pass_resortsNo check listed here called it with a valid call.
compare_passesNo check listed here called it with a valid call.
compare_resortsNo check listed here called it with a valid call.
get_my_snow_reportNo check listed here called it with a valid call.
get_storm_watchNo check listed here called it with a valid call.
get_avalancheNo check listed here called it with a valid call.
get_snow_qualityNo check listed here called it with a valid call.
get_operating_riskNo check listed here called it with a valid call.
get_road_accessNo check listed here called it with a valid call.
get_road_camerasNo check listed here called it with a valid call.
get_road_weatherNo check listed here called it with a valid call.
plan_ski_road_tripNo check listed here called it with a valid call.
find_flights_to_powderNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

Same as that run: the same grade in every test area, the same server version (3.7.0), the same Sealmark version (1.0.1).

  1. Bv3.7.0Sealmark 1.0.0
  2. Bv3.7.0Sealmark 1.0.1
  3. Bv3.7.0Sealmark 1.0.1

Badge for the README

The badge shows this automated result for version 3.7.0. It is a link to this page, not a certificate, and it changes when the next re-test does.

Sealmark badge for snowsure-mcp-server
The flat badge, one letter per graded test area.
[![Sealmark](https://sealmark.dev/badge/snowsure-mcp-server.svg)](https://sealmark.dev/results/snowsure-mcp-server/)

Files: badge SVG, card SVG, shields endpoint JSON.

Package facts

License
MIT
Latest release
3.7.0, published 2 Jul 2026 (the version graded on this page)

From npm, checked 22 Nov 2026. Plain facts about the package; they play no part in the grade.

Add it to an MCP client

This starts version 3.7.0, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "snowsure-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "snowsure-mcp-server@3.7.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add snowsure-mcp-server -- npx -y "snowsure-mcp-server@3.7.0"

The test run started the server with no API keys or other secrets, and with a cleaned environment. If the server needs some, its own documentation says how to pass them.

Run it yourself

This repeats the run with the same Sealmark version and the standard settings, starting the server the same way:

npx -y sealmark@1.0.1 run --start "npx -y snowsure-mcp-server@3.7.0"

To confirm your run used the standard settings, add --format json --out report.json to the command. In the report, config.standard should be true and config.hash should start with sha256:d13e7893a0ac, as they did in this run. If either differs, so did the settings, and the verdicts may too (STANDARD and CUSTOM runs).

To keep the setup, put the start command in sealmark.yaml as the server.

Grade alerts

One email when the grade of snowsure-mcp-server changes after a re-test. Nothing else, and every email has a link to stop them.

Or follow it in a feed reader: the Atom feed lists each move of the overall grade that came with a different version of this server, tested with the same Sealmark version as the graded run before.

Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.

Is this wrong?

Reply on the GitHub issue or email disclosure@sealmark.dev and we will recheck it. Maintainers can ask for their server to be removed.

If we were wrong, we correct the page and add your reply. Security findings go to the maintainer privately first; see the disclosure policy.