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

Results / @userintuition-ai/mcp

@userintuition-ai/mcp

version tested 1.6.4npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run79 tools

Sealmark's automated test of @userintuition-ai/mcp 1.6.4 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B). None of the 79 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, 4 inconclusive and 2 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 2 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

None of the 79 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, 79 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server User Intuition 1.6.4 answered; 79 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
1 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
124 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 124 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 124 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 (study_plan)
refusal-quality (advisory)
Refusals say what to do next
fail
0 of 9 refusal(s) say what to do instead or why retrying will not help (0 %)

Network checks

CheckVerdictWhat happened
net-loopback-ssrfcritical
Refuses loopback targets (SSRF)
inconclusive
the listener saw nothing, but 9 of 18 probes were not explicitly refused (9 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 6 of 12 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
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
create_studyNo check listed here called it with a valid call.None
customize_studyNo check listed here called it with a valid call.None
queue_customize_studyNo check listed here called it with a valid call.None
get_customize_study_jobNo check listed here called it with a valid call.None
get_studyNo check listed here called it with a valid call.None
review_studyNo check listed here called it with a valid call.None
estimate_panelNo check listed here called it with a valid call.None
launch_panelNo check listed here called it with a valid call.None
approve_panel_launchNo check listed here called it with a valid call.None
create_participantsNo check listed here called it with a valid call.None
get_participant_jobNo check listed here called it with a valid call.None
get_fielding_progressNo check listed here called it with a valid call.None
generate_reportNo check listed here called it with a valid call.None
get_report_jobNo check listed here called it with a valid call.None
get_study_reportNo check listed here called it with a valid call.None
answer_researchNo check listed here called it with a valid call.None
search_researchNo check listed here called it with a valid call.None
chat_research_sessionNo check listed here called it with a valid call.None
view_research_answerNo check listed here called it with a valid call.None
list_studiesNo check listed here called it with a valid call.None
list_organizationsNo check listed here called it with a valid call.None
get_accountNo check listed here called it with a valid call.None
update_studyNo check listed here called it with a valid call.None
delete_studyNo check listed here called it with a valid call.None
pause_studyNo check listed here called it with a valid call.None
resume_studyNo check listed here called it with a valid call.
stop_studyNo check listed here called it with a valid call.
queue_report_slidesNo check listed here called it with a valid call.
get_report_slide_jobNo check listed here called it with a valid call.
list_participantsNo check listed here called it with a valid call.
get_participantNo check listed here called it with a valid call.
update_participantNo check listed here called it with a valid call.
send_participant_rewardNo check listed here called it with a valid call.
delete_participantNo check listed here called it with a valid call.
list_interviewsNo check listed here called it with a valid call.
get_interviewNo check listed here called it with a valid call.
delete_interviewNo check listed here called it with a valid call.
list_targeting_attributesNo check listed here called it with a valid call.
create_research_sessionNo check listed here called it with a valid call.
rename_research_sessionNo check listed here called it with a valid call.
delete_research_sessionNo check listed here called it with a valid call.
sync_research_studyNo check listed here called it with a valid call.
remove_research_studyNo check listed here called it with a valid call.
remove_research_sourceNo check listed here called it with a valid call.
start_research_analysisNo check listed here called it with a valid call.
resume_research_analysisNo check listed here called it with a valid call.
cancel_research_analysisNo check listed here called it with a valid call.
get_research_analysisNo check listed here called it with a valid call.
queue_research_deliverableNo check listed here called it with a valid call.
get_research_deliverableNo check listed here called it with a valid call.
cancel_research_deliverableNo check listed here called it with a valid call.
inspect_research_sessionNo check listed here called it with a valid call.
upload_research_sourceNo check listed here called it with a valid call.
queue_research_chatNo check listed here called it with a valid call.
generate_research_outputNo check listed here called it with a valid call.
edit_research_outputNo check listed here called it with a valid call.
rename_research_outputNo check listed here called it with a valid call.
delete_research_outputNo check listed here called it with a valid call.
upload_research_templateNo check listed here called it with a valid call.
download_research_outputNo check listed here called it with a valid call.
get_interview_usage_statsNo check listed here called it with a valid call.
create_webhookNo check listed here called it with a valid call.
list_webhooksNo check listed here called it with a valid call.
get_webhookNo check listed here called it with a valid call.
rotate_webhook_secretNo check listed here called it with a valid call.
test_webhookNo check listed here called it with a valid call.
list_webhook_deliveriesNo check listed here called it with a valid call.
delete_webhook_by_idNo check listed here called it with a valid call.
delete_webhookNo check listed here called it with a valid call.
get_external_panelNo check listed here called it with a valid call.
configure_external_panelNo check listed here called it with a valid call.
regenerate_external_panel_tokenNo check listed here called it with a valid call.
delete_external_panelNo check listed here called it with a valid call.
submit_feasibility_requestNo check listed here called it with a valid call.
list_feasibility_requestsNo check listed here called it with a valid call.
get_feasibility_requestNo check listed here called it with a valid call.
cancel_feasibility_requestNo check listed here called it with a valid call.
add_all_research_studiesNo check listed here called it with a valid call.
clear_research_sourcesNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

  • Server version changed from 1.6.3 to 1.6.4.

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

  1. Bv1.6.2Sealmark 1.0.0
  2. Bv1.6.3Sealmark 1.0.0
  3. Bv1.6.3Sealmark 1.0.1
  4. Bv1.6.4Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.6.4, published 20 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 1.6.4, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "userintuition-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@userintuition-ai/mcp@1.6.4"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add userintuition-ai-mcp -- npx -y "@userintuition-ai/mcp@1.6.4"

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 @userintuition-ai/mcp@1.6.4"

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 @userintuition-ai/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.