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

Results / @fictura/mcp

@fictura/mcp

version tested 0.1.2npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run88 tools

Sealmark's automated test of @fictura/mcp 0.1.2 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol A and effects B). Only 35 of 88 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 10 checks, 5 passed, 1 partial, 2 inconclusive and 2 not applicable. 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

Only 35 of 88 tools could be called with default settings, so the deeper test areas cover only those tools.

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, 88 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server fictura 1.0.0 answered; 88 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 88 tool definition(s), the server instructions and serverInfo, 1 prompt(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
95 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 95 invalid call(s) across 19 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 101 captured response(s), 1 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

Network checks

CheckVerdictWhat happened
net-loopback-ssrfcritical
Refuses loopback targets (SSRF)
inconclusive
the listener saw nothing, but 18 of 18 probes were not explicitly refused (18 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 12 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-honestyweak signal
Read-only tools change nothing
partial
declared read-only; only caches changed (sandbox home or temp): get_app_setup, get_setup_status, list_users, get_tracking_plan, list_surfaces, list_experiments, get_store_analytics, list_creators, get_push_config, list_store_products, list_error_issues, search_error_issues, search_error_events, get_error_event, search_logs, search_traces, list_error_alerts, list_alert_rules, list_releases, list_inbound_filters, get_uptime_monitor, get_error_settings, get_performance_overview, list_dependencies, get_ai_usage, get_jobs, get_web_vitals, get_mobile_vitals, list_monitors, get_tracing_health, get_appsflyer_import_status, get_appsflyer_attribution_summary (read_doc 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
35 closed-world tool(s) called; none reached out beyond what was asked
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
search_docsNo check listed here called it with a valid call.None
list_docsNone
read_docNo check listed here called it with a valid call.None
get_app_setupNo check listed here called it with a valid call.
get_setup_stepNo check listed here called it with a valid call.None
get_setup_statusNo check listed here called it with a valid call.
update_app_identityNo check listed here called it with a valid call.None
create_tracking_linkNo check listed here called it with a valid call.None
get_analyticsNo check listed here called it with a valid call.None
get_attribution_reportNo check listed here called it with a valid call.None
list_usersNo check listed here called it with a valid call.None
get_userNo check listed here called it with a valid call.None
check_entitlementNo check listed here called it with a valid call.None
get_tracking_planNo check listed here called it with a valid call.
get_event_analyticsNo check listed here called it with a valid call.None
list_surfacesNo check listed here called it with a valid call.
get_surfaceNo check listed here called it with a valid call.None
list_templatesNo check listed here called it with a valid call.None
list_experimentsNo check listed here called it with a valid call.
get_experimentNo check listed here called it with a valid call.None
create_experimentNo check listed here called it with a valid call.None
start_experimentNo check listed here called it with a valid call.None
pause_experimentNo check listed here called it with a valid call.None
resume_experimentNo check listed here called it with a valid call.None
stop_experimentNo check listed here called it with a valid call.None
get_acquisition_reportNo check listed here called it with a valid call.
get_store_analyticsNo check listed here called it with a valid call.
list_campaignsNo check listed here called it with a valid call.
list_creatorsNo check listed here called it with a valid call.
get_link_infrastructureNo check listed here called it with a valid call.
get_push_configNo check listed here called it with a valid call.
list_store_productsNo check listed here called it with a valid call.
list_error_issuesNo check listed here called it with a valid call.
search_error_issuesNo check listed here called it with a valid call.
search_error_eventsNo check listed here called it with a valid call.
get_error_eventNo check listed here called it with a valid call.
get_error_issueNo check listed here called it with a valid call.
get_error_issue_briefNo check listed here called it with a valid call.
get_issue_tag_valuesNo check listed here called it with a valid call.
get_issue_activityNo check listed here called it with a valid call.
search_logsNo check listed here called it with a valid call.
search_tracesNo check listed here called it with a valid call.
get_traceNo check listed here called it with a valid call.
list_error_alertsNo check listed here called it with a valid call.
list_alert_rulesNo check listed here called it with a valid call.
list_releasesNo check listed here called it with a valid call.
update_error_issueNo check listed here called it with a valid call.
update_error_issuesNo check listed here called it with a valid call.
list_inbound_filtersNo check listed here called it with a valid call.
create_inbound_filterNo check listed here called it with a valid call.
delete_inbound_filterNo check listed here called it with a valid call.
get_uptime_monitorNo check listed here called it with a valid call.
set_uptime_monitorNo check listed here called it with a valid call.
get_error_settingsNo check listed here called it with a valid call.
update_tracing_settingsNo check listed here called it with a valid call.
get_performance_overviewNo check listed here called it with a valid call.
get_endpoint_summaryNo check listed here called it with a valid call.
list_dependenciesNo check listed here called it with a valid call.
get_spanNo check listed here called it with a valid call.
get_ai_usageNo check listed here called it with a valid call.
get_jobsNo check listed here called it with a valid call.
compare_releasesNo check listed here called it with a valid call.
get_web_vitalsNo check listed here called it with a valid call.
get_mobile_vitalsNo check listed here called it with a valid call.
list_monitorsNo check listed here called it with a valid call.
get_tracing_healthNo check listed here called it with a valid call.
create_ticketNo check listed here called it with a valid call.
link_pull_requestNo check listed here called it with a valid call.
create_fix_prNo check listed here called it with a valid call.
create_pull_requestNo check listed here called it with a valid call.
get_pull_request_statusNo check listed here called it with a valid call.
start_fix_runNo check listed here called it with a valid call.
get_fix_runNo check listed here called it with a valid call.
get_paywall_docNo check listed here called it with a valid call.
validate_paywall_docNo check listed here called it with a valid call.
save_paywall_docNo check listed here called it with a valid call.
create_paywall_draftNo check listed here called it with a valid call.
pair_editorNo check listed here called it with a valid call.
editor_get_docNo check listed here called it with a valid call.
editor_set_docNo check listed here called it with a valid call.
unpair_editorNo check listed here called it with a valid call.
get_onboarding_docNo check listed here called it with a valid call.
validate_onboarding_docNo check listed here called it with a valid call.
save_onboarding_docNo check listed here called it with a valid call.
create_onboarding_draftNo check listed here called it with a valid call.
start_appsflyer_importNo check listed here called it with a valid call.
get_appsflyer_import_statusNo check listed here called it with a valid call.
get_appsflyer_attribution_summaryNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

  • The server listed 88 tools, 1 more than before (87).

Unchanged: the same grade in every test area, the same server version (0.1.2), the same Sealmark version (1.0.1).

  1. Bv0.1.2Sealmark 1.0.0
  2. Bv0.1.2Sealmark 1.0.1
  3. Bv0.1.2Sealmark 1.0.1

Package facts

License
MIT
Latest release
0.1.2, published 29 Oct 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 0.1.2, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "fictura-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fictura/mcp@0.1.2"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add fictura-mcp -- npx -y "@fictura/mcp@0.1.2"

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 @fictura/mcp@0.1.2"

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 @fictura/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.