Sealmark
Automated re-test on 2026-11-22: not checked by hand, and not yet reviewed by the maintainers.

Results / @trusty-squire/mcp

@trusty-squire/mcp

version tested 1.1.61npmtested 2026-11-22Sealmark 1.0.1methodology 0.3-draftSTANDARD run34 tools

Sealmark's automated test of @trusty-squire/mcp 1.1.61 on 2026-11-22 gave it grade B, its lowest test-area grade (protocol B). Only 4 of 34 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 3 passed, 1 partial, 3 inconclusive and 3 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 1 passed, 1 failed and 1 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

Only 4 of 34 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

B
Protocol3.5/4 pointsincludes a weak signal, not a security finding

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 34 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server trusty-squire 1.1.61 answered; 34 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
2 weak indicator(s) worth reading, none conclusive
Weak signal, not a security finding. Some wording in the tool text is worth a read, but none of it is conclusive. A partial counts as half a point.
robust-input
Survives malformed tool input
pass
112 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 112 invalid call(s) across 23 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 114 captured response(s), 0 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 1 tool(s) the server does not offer (allowed_hosts)
refusal-quality (advisory)
Refusals say what to do next
n/a
no refusal was recorded in this run, so there is nothing to judge

Network checks

CheckVerdictWhat happened
net-loopback-ssrfcritical
Refuses loopback targets (SSRF)
inconclusive
the listener saw nothing, but 45 of 45 probes were not explicitly refused (45 failed without saying the target was refused), so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
net-scheme-allowlistcritical
Only http(s) schemes accepted
inconclusive
no scheme had an observable effect, but 30 of 30 scored probes were not explicitly refused, so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
net-caps
Response size and time are capped
n/a
net-loopback-ssrf was inconclusive: the server never reached the loopback listener, so no loopback URL is known to be fetchable; response size and time caps were not measured
net-redirect
Redirects are re-validated
n/a
the server refused or never reached the loopback listener, so redirect handling could not be observed (a server that blocks loopback cannot be sent a redirect it would follow)

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
n/a
no tool declares openWorldHint: false that could be given a harness-owned control argument
undeclared-writes (advisory)
Unannotated tools leave the sandbox unchanged
pass
operate_download carry no annotations and changed nothing

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
list_credentialsNo check listed here called it with a valid call.None
store_credentialNo check listed here called it with a valid call.None
edit_credentialNo check listed here called it with a valid call.None
delete_credentialNo check listed here called it with a valid call.None
use_credentialNo check listed here called it with a valid call.None
fetch_credentialNo check listed here called it with a valid call.None
grant_app_accessNo check listed here called it with a valid call.None
list_app_accessNo check listed here called it with a valid call.
revoke_app_accessNo check listed here called it with a valid call.None
audit_logNo check listed here called it with a valid call.None
list_payment_cardsNo check listed here called it with a valid call.
edit_payment_cardNo check listed here called it with a valid call.None
inject_cardNo check listed here called it with a valid call.None
operate_startNo check listed here called it with a valid call.
operate_driveNo check listed here called it with a valid call.
operate_finishNo check listed here called it with a valid call.None
operate_observeNo check listed here called it with a valid call.None
operate_screenshotNo check listed here called it with a valid call.None
operate_networkNo check listed here called it with a valid call.None
operate_navigateNo check listed here called it with a valid call.
operate_clickNo check listed here called it with a valid call.None
operate_typeNo check listed here called it with a valid call.None
operate_selectNo check listed here called it with a valid call.None
operate_uploadNo check listed here called it with a valid call.
operate_downloadNone
operate_pressNo check listed here called it with a valid call.
operate_solve_captchaNo check listed here called it with a valid call.
operate_scrollNo check listed here called it with a valid call.
operate_waitNo check listed here called it with a valid call.
operate_read_inboxNo check listed here called it with a valid call.
operate_loginNo check listed here called it with a valid call.
operate_extractNo check listed here called it with a valid call.
operate_shareNo check listed here called it with a valid call.
operate_dialogNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

  • Server version changed from 1.1.43 to 1.1.61.
  • Input schema changed (any part of it, parameter wording included): operate_drive.

Unchanged: the same grade in every test area, the same Sealmark version (1.0.1).

  1. –did not run
  2. –did not run
  3. Bv1.1.44-rc.1Sealmark 1.0.1
  4. Bv1.1.43Sealmark 1.0.1
  5. Bv1.1.43Sealmark 1.0.1
  6. Bv1.1.61Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.1.43, published 15 Nov 2026. This page graded 1.1.61.
Repository
Trusty-Squire/trusty-squire
Last push
22 Nov 2026
Open issues and pull requests
8

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

{
  "mcpServers": {
    "trusty-squire-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@trusty-squire/mcp@1.1.61",
        "server"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add trusty-squire-mcp -- npx -y "@trusty-squire/mcp@1.1.61" server

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 @trusty-squire/mcp@1.1.61 server"

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 @trusty-squire/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.