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

Results / @ekwo-ai/mcp

@ekwo-ai/mcp

version tested 0.27.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run83 tools

Sealmark's automated test of @ekwo-ai/mcp 0.27.0 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). None of the 83 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 4 passed, 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.

A

Grade A

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

None of the 83 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, 83 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server @ekwo-ai/mcp 0.27.0 answered; 83 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 83 tool definition(s), the server instructions and serverInfo, 2 prompt(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
119 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 119 invalid call(s) across 24 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 120 captured response(s), 0 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 6 tool(s) the server does not offer (approval_required, autopilot_forbidden, period_locked, entry_unbalanced, document_total_mismatch)
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
every loopback probe was refused, but a data: URL with no host got the same reply word for word, so the refusal does not describe the target (the tool may refuse every URL; set net.control_url to a URL it can reach)
net-scheme-allowlistcritical
Only http(s) schemes accepted
inconclusive
no scheme had an observable effect, but no probe was refused for its scheme (the refusals were for another reason, a host guard says nothing about the scheme) and no fetch was shown to work (a tool that fetches nothing would pass; 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
list_companiesNo check listed here called it with a valid call.
get_companyNo check listed here called it with a valid call.None
list_accountsNo check listed here called it with a valid call.None
search_contactsNo check listed here called it with a valid call.None
suggest_duplicate_contactsNo check listed here called it with a valid call.None
contact_statementNo check listed here called it with a valid call.None
list_documentsNo check listed here called it with a valid call.None
get_documentNo check listed here called it with a valid call.None
render_invoice_pdfNo check listed here called it with a valid call.None
get_preferencesNo check listed here called it with a valid call.None
list_api_keysNo check listed here called it with a valid call.None
list_invitationsNo check listed here called it with a valid call.None
list_sharesNo check listed here called it with a valid call.None
list_bank_transactionsNo check listed here called it with a valid call.None
trial_balanceNo check listed here called it with a valid call.None
general_ledgerNo check listed here called it with a valid call.None
journal_bookNo check listed here called it with a valid call.None
suggest_line_contactsNo check listed here called it with a valid call.None
suggest_item_combinationsNo check listed here called it with a valid call.None
matching_difference_optionsNo check listed here called it with a valid call.None
aged_balanceNo check listed here called it with a valid call.None
subledgerNo check listed here called it with a valid call.None
vat_returnNo check listed here called it with a valid call.None
instalment_planNo check listed here called it with a valid call.None
ec_sales_listNo check listed here called it with a valid call.None
portfolio_upcoming_filingsNo check listed here called it with a valid call.
portfolio_filings_touched_sinceNo check listed here called it with a valid call.
portfolio_overviewNo check listed here called it with a valid call.
list_statementsNo check listed here called it with a valid call.
financial_statementNo check listed here called it with a valid call.
financial_analysisNo check listed here called it with a valid call.
list_analytic_axesNo check listed here called it with a valid call.
analytic_reportNo check listed here called it with a valid call.
generate_fecNo check listed here called it with a valid call.
describe_packNo check listed here called it with a valid call.
statusNo check listed here called it with a valid call.
read_audit_logNo check listed here called it with a valid call.
search_productsNo check listed here called it with a valid call.
create_productNo check listed here called it with a valid call.
update_productNo check listed here called it with a valid call.
create_contactNo check listed here called it with a valid call.
merge_contactsNo check listed here called it with a valid call.
create_documentNo check listed here called it with a valid call.
update_document_linesNo check listed here called it with a valid call.
post_documentNo check listed here called it with a valid call.
accept_documentNo check listed here called it with a valid call.
decline_documentNo check listed here called it with a valid call.
undo_document_answerNo check listed here called it with a valid call.
cancel_documentNo check listed here called it with a valid call.
reverse_entryNo check listed here called it with a valid call.
record_paymentNo check listed here called it with a valid call.
reconcileNo check listed here called it with a valid call.
unreconcileNo check listed here called it with a valid call.
set_line_contactNo check listed here called it with a valid call.
leave_line_unnamedNo check listed here called it with a valid call.
undo_leave_line_unnamedNo check listed here called it with a valid call.
reconcile_manyNo check listed here called it with a valid call.
reconcile_with_differenceNo check listed here called it with a valid call.
settle_from_statementNo check listed here called it with a valid call.
create_bank_accountNo check listed here called it with a valid call.
list_bank_accountsNo check listed here called it with a valid call.
update_bank_accountNo check listed here called it with a valid call.
create_bank_transactionNo check listed here called it with a valid call.
import_bank_statementNo check listed here called it with a valid call.
create_companyNo check listed here called it with a valid call.
update_company_profileNo check listed here called it with a valid call.
set_number_prefixNo check listed here called it with a valid call.
set_preferencesNo check listed here called it with a valid call.
invite_memberNo check listed here called it with a valid call.
create_api_keyNo check listed here called it with a valid call.
revoke_api_keyNo check listed here called it with a valid call.
revoke_invitationNo check listed here called it with a valid call.
remove_memberNo check listed here called it with a valid call.
set_member_roleNo check listed here called it with a valid call.
share_documentNo check listed here called it with a valid call.
revoke_shareNo check listed here called it with a valid call.
pin_accountsNo check listed here called it with a valid call.
lock_periodNo check listed here called it with a valid call.
import_booksNo check listed here called it with a valid call.
opening_balanceNo check listed here called it with a valid call.
close_fiscal_yearNo check listed here called it with a valid call.
reopen_fiscal_yearNo check listed here called it with a valid call.
close_fiscal_year_finallyNo 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 (0.27.0), the same Sealmark version (1.0.1).

  1. Av0.25.0Sealmark 1.0.0
  2. Av0.25.2Sealmark 1.0.0
  3. Av0.25.2Sealmark 1.0.1
  4. Av0.27.0Sealmark 1.0.1
  5. Av0.27.0Sealmark 1.0.1

Package facts

License
AGPL-3.0-only
Latest release
0.27.0, published 19 Nov 2026 (the version graded on this page)
Repository
Ekwo-ai/ekwo-os
Last push
21 Nov 2026
Open issues and pull requests
5

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

{
  "mcpServers": {
    "ekwo-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@ekwo-ai/mcp@0.27.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add ekwo-ai-mcp -- npx -y "@ekwo-ai/mcp@0.27.0"

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 @ekwo-ai/mcp@0.27.0"

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 @ekwo-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.