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

Results / @durely/garmin-insights-mcp

@durely/garmin-insights-mcp

version tested 0.5.2npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run21 tools

Sealmark's automated test of @durely/garmin-insights-mcp 0.5.2 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol A and effects B). Tools reached with a valid call: 13 of 21. Of its 6 checks, 5 passed and 1 partial. 3 more checks are advisory, and advisory checks never change a grade: 1 passed and 2 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: 13 of 21.

Grade by test area

A
Protocol4/4 points
B
Effects1.5/2 pointsincludes a weak signal, not a security finding

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 21 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server garmin-insights-mcp 0.5.2 answered; 21 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 21 tool definition(s), the server instructions and serverInfo, 3 prompt(s) and 1 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
90 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 90 invalid call(s) across 21 tool(s)
    Outcome all rejected cleanly and the server stayed responsive
    Decided from the MCP exchange (protocol)
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 90 captured response(s), 0 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
pass
the instructions name no tool the server lacks
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-honestyweak signal
Read-only tools change nothing
partial
declared read-only; only caches changed (sandbox home or temp): garmin_list_activities, garmin_get_daily_health, garmin_get_sleep, garmin_get_hrv, garmin_get_body_composition, garmin_training_summary, garmin_recovery_trends (garmin_get_profile, garmin_get_intraday, garmin_get_nutrition, garmin_get_womens_health not judged: the control call failed)
Weak signal, not a security finding. A tool declared read-only changed only cache files, in its sandbox home or temp folder. A partial counts as half a point.
openworld-honesty
Closed-world tools stay on the machine
pass
1 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
garmin_statusNo check listed here called it with a valid call.None
garmin_get_profileNo check listed here called it with a valid call.None
garmin_list_activitiesNo check listed here called it with a valid call.None
garmin_get_activityNo check listed here called it with a valid call.None
garmin_get_activity_lapsNo check listed here called it with a valid call.None
garmin_get_activity_streamsNo check listed here called it with a valid call.None
garmin_download_activity_fitNo check listed here called it with a valid call.None
garmin_get_daily_healthNo check listed here called it with a valid call.None
garmin_get_sleepNo check listed here called it with a valid call.None
garmin_get_hrvNo check listed here called it with a valid call.None
garmin_get_intradayNo check listed here called it with a valid call.None
garmin_get_body_compositionNo check listed here called it with a valid call.None
garmin_get_nutritionNo check listed here called it with a valid call.None
garmin_get_womens_healthNo check listed here called it with a valid call.None
garmin_analyze_activityNo check listed here called it with a valid call.None
garmin_training_summaryNo check listed here called it with a valid call.None
garmin_recovery_trendsNo check listed here called it with a valid call.None
garmin_compare_activitiesNo check listed here called it with a valid call.None
garmin_queryNo check listed here called it with a valid call.None
garmin_syncNo check listed here called it with a valid call.None
garmin_sync_statusNo check listed here called it with a valid call.None

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 (0.5.2), the same Sealmark version (1.0.1).

  1. Bv0.5.2Sealmark 1.0.0
  2. Bv0.5.2Sealmark 1.0.1
  3. Bv0.5.2Sealmark 1.0.1

Badge for the README

The badge shows this automated result for version 0.5.2. It is a link to this page, not a certificate, and it changes when the next re-test does.

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

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

Package facts

License
Apache-2.0
Latest release
0.5.2, published 29 Oct 2026 (the version graded on this page)
Repository
durely/garmin-insights-mcp
Last push
18 Nov 2026
Open issues and pull requests
0

From npm and GitHub, 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 0.5.2, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "durely-garmin-insights-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@durely/garmin-insights-mcp@0.5.2"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add durely-garmin-insights-mcp -- npx -y "@durely/garmin-insights-mcp@0.5.2"

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 @durely/garmin-insights-mcp@0.5.2"

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 @durely/garmin-insights-mcp 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.