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

Results / storkai

storkai

version tested 2.3.2npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run30 tools

Sealmark's automated test of storkai 2.3.2 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B and effects A). Only 6 of 30 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 10 checks, 4 passed, 1 partial, 2 inconclusive and 3 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 3 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 6 of 30 tools could be called with default settings, so the deeper test areas cover only those tools.

Grade by test area

B
Protocol3.5/4 points
A
Effects1/1 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 30 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server storkai 2.3.1 answered; 30 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 30 tool definition(s) and serverInfo, 4 prompt(s) and 2 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
partial
0 internals leak(s), 51 invalid call(s) accepted
Evidence for robust-input: first 6 of 51 lines
  1. Probe stork_search: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool stork_search
  2. Probe stork_smithery_replacement: required arguments missing
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool stork_smithery_replacement
  3. Probe stork_smithery_replacement: every typed argument has the wrong type
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool stork_smithery_replacement
  4. Probe stork_smithery_replacement: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool stork_smithery_replacement
  5. Probe stork_smithery_replacement: wrong types plus an unexpected extra argument
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool stork_smithery_replacement
  6. Probe stork_smithery_replacement: every string argument is an object
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool stork_smithery_replacement
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 113 captured response(s), 52 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
n/a
the server sent no instructions
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 9 of 9 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 6 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
pass
stork_search, stork_list_filters, stork_tools_search, stork_tools_categories declared read-only and changed nothing in the observed directories during a benign call (stork_scrape, stork_repo not judged: the control call failed)
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
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
stork_searchNo check listed here called it with a valid call.None
stork_server_detailsNo check listed here called it with a valid call.None
stork_get_install_configNo check listed here called it with a valid call.None
stork_compareNo check listed here called it with a valid call.None
stork_list_filtersNone
stork_smithery_replacementNo check listed here called it with a valid call.None
stork_web_searchNo check listed here called it with a valid call.None
stork_scrapeNo check listed here called it with a valid call.None
stork_docsNo check listed here called it with a valid call.None
stork_repoNo check listed here called it with a valid call.None
stork_installNo check listed here called it with a valid call.None
stork_server_docsNo check listed here called it with a valid call.None
stork_tool_schemaNo check listed here called it with a valid call.None
stork_callNo check listed here called it with a valid call.None
stork_discover_payable_servicesNo check listed here called it with a valid call.None
stork_run_toolNo check listed here called it with a valid call.None
stork_talking_photo_voicesNo check listed here called it with a valid call.None
stork_talking_photo_estimateNo check listed here called it with a valid call.None
stork_talking_photo_createNo check listed here called it with a valid call.None
stork_talking_photo_statusNo check listed here called it with a valid call.None
stork_singing_video_estimateNo check listed here called it with a valid call.None
stork_singing_video_createNo check listed here called it with a valid call.None
stork_singing_video_statusNo check listed here called it with a valid call.None
stork_llm_pricesNo check listed here called it with a valid call.None
stork_tools_searchNo check listed here called it with a valid call.None
stork_tools_detailsNo check listed here called it with a valid call.
stork_tools_compareNo check listed here called it with a valid call.
stork_tools_recommendNo check listed here called it with a valid call.
stork_tools_alternativesNo check listed here called it with a valid call.
stork_tools_categoriesNo check listed here called it with a valid call.

What was not covered

Grade over time

Since the run on

  • Server version changed from 2.3.1 to 2.3.2.

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

  1. Bv2.2.0Sealmark 1.0.1
  2. Bv2.3.0Sealmark 1.0.1
  3. Bv2.3.1Sealmark 1.0.1
  4. Bv2.3.2Sealmark 1.0.1

Package facts

License
MIT
Latest release
2.3.2, published 19 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 2.3.2, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "storkai": {
      "command": "npx",
      "args": [
        "-y",
        "storkai@2.3.2"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add storkai -- npx -y "storkai@2.3.2"

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 storkai@2.3.2"

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 storkai 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.