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

Results / @stratta/mcp

@stratta/mcp

version tested 1.22.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run60 tools

Sealmark's automated test of @stratta/mcp 1.22.0 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). None of the 60 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 6 checks, 4 passed and 2 inconclusive. 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.

A

Grade A

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

None of the 60 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

A
Protocol4/4 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 60 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server stratta-mcp 1.22.0 answered; 60 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 60 tool definition(s), the server instructions and serverInfo, 4 prompt(s) and 2 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
107 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 107 invalid call(s) across 22 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 110 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-honestycritical
Read-only tools change nothing
inconclusive
every control call failed, so the read-only annotation could not be checked
openworld-honesty
Closed-world tools stay on the machine
inconclusive
every control call failed, so the closed-world annotation could not be checked
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
get_methodologyNo check listed here called it with a valid call.
whoamiNo check listed here called it with a valid call.
list_normsNo check listed here called it with a valid call.None
get_tocNo check listed here called it with a valid call.None
get_subtreeNo check listed here called it with a valid call.None
get_sectionNo check listed here called it with a valid call.None
search_in_normNo check listed here called it with a valid call.None
search_corpusNo check listed here called it with a valid call.None
get_cross_refsNo check listed here called it with a valid call.None
verify_citationNo check listed here called it with a valid call.None
get_figureNo check listed here called it with a valid call.None
scan_siteNo check listed here called it with a valid call.None
get_site_contextNo check listed here called it with a valid call.None
get_boreholesNo check listed here called it with a valid call.None
list_sitesNo check listed here called it with a valid call.None
get_siteNo check listed here called it with a valid call.None
get_site_sectionNo check listed here called it with a valid call.None
list_site_overlaysNo check listed here called it with a valid call.None
get_groundwater_contoursNo check listed here called it with a valid call.None
list_site_photosNo check listed here called it with a valid call.None
list_site_neighboursNo check listed here called it with a valid call.None
list_dossiersNo check listed here called it with a valid call.
open_dossierNo check listed here called it with a valid call.None
open_questionNo check listed here called it with a valid call.None
save_findingNo check listed here called it with a valid call.None
record_decisionNo check listed here called it with a valid call.
load_dossierNo check listed here called it with a valid call.
resolve_questionNo check listed here called it with a valid call.
list_attachmentsNo check listed here called it with a valid call.
read_attachmentNo check listed here called it with a valid call.
search_in_dossierNo check listed here called it with a valid call.
add_attachmentNo check listed here called it with a valid call.
list_templatesNo check listed here called it with a valid call.
apply_templateNo check listed here called it with a valid call.
draft_deliverableNo check listed here called it with a valid call.
write_sectionNo check listed here called it with a valid call.
list_questionsNo check listed here called it with a valid call.
get_questionNo check listed here called it with a valid call.
get_dossier_activityNo check listed here called it with a valid call.
list_exportsNo check listed here called it with a valid call.
update_questionNo check listed here called it with a valid call.
add_optionNo check listed here called it with a valid call.
update_optionNo check listed here called it with a valid call.
delete_optionNo check listed here called it with a valid call.
delete_questionNo check listed here called it with a valid call.
add_commentNo check listed here called it with a valid call.
update_entryNo check listed here called it with a valid call.
attach_entryNo check listed here called it with a valid call.
list_skillsNo check listed here called it with a valid call.
get_skillNo check listed here called it with a valid call.
ingest_statusNo check listed here called it with a valid call.
ingest_create_documentNo check listed here called it with a valid call.
ingest_create_sectionsNo check listed here called it with a valid call.
ingest_attach_formulaNo check listed here called it with a valid call.
ingest_attach_tableNo check listed here called it with a valid call.
ingest_attach_cross_refNo check listed here called it with a valid call.
ingest_upload_figureNo check listed here called it with a valid call.
ingest_normalize_cross_refsNo check listed here called it with a valid call.
ingest_publishNo check listed here called it with a valid call.
ingest_deleteNo 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 (1.22.0), the same Sealmark version (1.0.1).

  1. Av1.20.1Sealmark 1.0.0
  2. Av1.21.0Sealmark 1.0.0
  3. Av1.22.0Sealmark 1.0.1
  4. Av1.22.0Sealmark 1.0.1

Package facts

License
UNLICENSED (npm's word for no rights granted to others)
Latest release
1.22.0, published 13 Nov 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 1.22.0, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "stratta-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@stratta/mcp@1.22.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add stratta-mcp -- npx -y "@stratta/mcp@1.22.0"

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 @stratta/mcp@1.22.0"

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 @stratta/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.