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

Results / qiksy-mcp

qiksy-mcp

version tested 1.87.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run82 tools

Sealmark's automated test of qiksy-mcp 1.87.0 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). Only 3 of 82 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 4 passed, 2 inconclusive and 4 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.

A

Grade A

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

Only 3 of 82 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, 82 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server qiksy 1.87.0 answered; 82 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 82 tool definition(s), the server instructions and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
104 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 104 invalid call(s) across 25 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 104 captured response(s), 0 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 3 tool(s) the server does not offer (modal, browser, qiksySays)
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 54 of 54 probes were not explicitly refused (27 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 36 of 36 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
n/a
no tool declares readOnlyHint: true
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
qa_failure_gallery, qa_pick_path, qa_scenario_get 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
qa_collectNo check listed here called it with a valid call.None
qa_stepsNo check listed here called it with a valid call.None
qa_watchNo check listed here called it with a valid call.
qa_diffNo check listed here called it with a valid call.None
qa_open_tabNo check listed here called it with a valid call.
qa_width_lawNo check listed here called it with a valid call.None
qa_odd_one_outNo check listed here called it with a valid call.None
qa_shot_listNo check listed here called it with a valid call.None
qa_shot_readNo check listed here called it with a valid call.None
qa_shot_markNo check listed here called it with a valid call.None
qa_shot_cropNo check listed here called it with a valid call.None
qa_shot_dropNo check listed here called it with a valid call.None
qa_report_buildNo check listed here called it with a valid call.None
qa_draftNo check listed here called it with a valid call.None
qa_draft_addNo check listed here called it with a valid call.None
qa_draft_editNo check listed here called it with a valid call.None
qa_draft_moveNo check listed here called it with a valid call.None
qa_draft_dropNo check listed here called it with a valid call.None
qa_draft_metaNo check listed here called it with a valid call.None
qa_draft_clearNo check listed here called it with a valid call.None
qa_draft_buildNo check listed here called it with a valid call.None
qa_report_editNo check listed here called it with a valid call.None
qa_reportsNo check listed here called it with a valid call.None
qa_report_getNo check listed here called it with a valid call.None
qa_report_dropNo check listed here called it with a valid call.None
qa_wiringNo check listed here called it with a valid call.
qa_focus_proofNo check listed here called it with a valid call.
qa_annotateNo check listed here called it with a valid call.
qa_failure_gallery
qa_gapNo check listed here called it with a valid call.
qa_framesNo check listed here called it with a valid call.
qa_tabsNo check listed here called it with a valid call.
qa_statusNo check listed here called it with a valid call.
qa_findingsNo check listed here called it with a valid call.
qa_exportNo check listed here called it with a valid call.
qa_open_panelNo check listed here called it with a valid call.
qa_run_auditNo check listed here called it with a valid call.
qa_axeNo check listed here called it with a valid call.
qa_readNo check listed here called it with a valid call.
qa_uploadNo check listed here called it with a valid call.
qa_storageNo check listed here called it with a valid call.
qa_dialogsNo check listed here called it with a valid call.
qa_mockNo check listed here called it with a valid call.
qa_stylesNo check listed here called it with a valid call.
qa_snapshotNo check listed here called it with a valid call.
qa_tourNo check listed here called it with a valid call.
qa_reportNo check listed here called it with a valid call.
qa_spotlightNo check listed here called it with a valid call.
qa_click_pointNo check listed here called it with a valid call.
qa_drag_pointNo check listed here called it with a valid call.
qa_hoverNo check listed here called it with a valid call.
qa_clickNo check listed here called it with a valid call.
qa_typeNo check listed here called it with a valid call.
qa_type_manyNo check listed here called it with a valid call.
qa_pressNo check listed here called it with a valid call.
qa_wait_readyNo check listed here called it with a valid call.
qa_wait_forNo check listed here called it with a valid call.
qa_followNo check listed here called it with a valid call.
qa_helpNo check listed here called it with a valid call.
qa_screenshotNo check listed here called it with a valid call.
qa_navigateNo check listed here called it with a valid call.
qa_reloadNo check listed here called it with a valid call.
qa_open_isolatedNo check listed here called it with a valid call.
qa_focus_tabNo check listed here called it with a valid call.
qa_doneNo check listed here called it with a valid call.
qa_close_tabNo check listed here called it with a valid call.
qa_fill_jsonNo check listed here called it with a valid call.
qa_pick_dateNo check listed here called it with a valid call.
qa_pick_path
qa_pick_tagsNo check listed here called it with a valid call.
qa_pick_timeNo check listed here called it with a valid call.
qa_pick_rangeNo check listed here called it with a valid call.
qa_focus_walkNo check listed here called it with a valid call.
qa_probeNo check listed here called it with a valid call.
qa_recipe_saveNo check listed here called it with a valid call.
qa_recipe_listNo check listed here called it with a valid call.
qa_recipe_applyNo check listed here called it with a valid call.
qa_suite_runNo check listed here called it with a valid call.
qa_scenariosNo check listed here called it with a valid call.
qa_scenario_get
qa_scenario_saveNo check listed here called it with a valid call.
qa_scenario_runNo 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 tools with the same input schemas, the same server version (1.87.0), the same Sealmark version (1.0.1).

  1. Av1.87.0Sealmark 1.0.1
  2. Av1.87.0Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.87.0, published 17 Nov 2026 (the version graded on this page)
Repository
lesnyak-cyber/qiksy-mcp
Last push
17 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 1.87.0, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "qiksy-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "qiksy-mcp@1.87.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add qiksy-mcp -- npx -y "qiksy-mcp@1.87.0"

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 qiksy-mcp@1.87.0"

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 qiksy-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.