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

Results / @aetherwealth/mcp

@aetherwealth/mcp

version tested 0.2.17npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run49 tools

Sealmark's automated test of @aetherwealth/mcp 0.2.17 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). None of the 49 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 4 checks, 4 passed. 2 more checks are advisory, and advisory checks never change a grade: 2 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 49 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, 49 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server aether-wealth-mcp 0.2.17 answered; 49 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 49 tool definition(s) and serverInfo, 2 prompt(s) and 1 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
105 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 105 invalid call(s) across 21 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 105 captured response(s), 0 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

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
loginNo check listed here called it with a valid call.
logoutNo check listed here called it with a valid call.
get_contextNo check listed here called it with a valid call.
list_tradesNo check listed here called it with a valid call.None
get_tradeNo check listed here called it with a valid call.None
list_accountsNo check listed here called it with a valid call.
create_accountNo check listed here called it with a valid call.None
trade_statsNo check listed here called it with a valid call.None
create_tradeNo check listed here called it with a valid call.None
update_tradeNo check listed here called it with a valid call.None
close_tradeNo check listed here called it with a valid call.None
delete_tradeNo check listed here called it with a valid call.None
delete_tradesNo check listed here called it with a valid call.None
import_tradesNo check listed here called it with a valid call.None
get_broker_accountNo check listed here called it with a valid call.None
list_broker_positionsNo check listed here called it with a valid call.None
get_broker_quoteNo check listed here called it with a valid call.None
connect_brokerNo check listed here called it with a valid call.None
broker_connection_statusNo check listed here called it with a valid call.None
disconnect_brokerNo check listed here called it with a valid call.None
set_broker_approval_modeNo check listed here called it with a valid call.None
propose_tradeNo check listed here called it with a valid call.None
execute_tradeNo check listed here called it with a valid call.None
trade_intent_statusNo check listed here called it with a valid call.None
cancel_trade_intentNo check listed here called it with a valid call.None
close_positionNo check listed here called it with a valid call.
modify_positionNo check listed here called it with a valid call.
list_alertsNo check listed here called it with a valid call.
create_price_alertNo check listed here called it with a valid call.
create_trendline_alertNo check listed here called it with a valid call.
update_alertNo check listed here called it with a valid call.
delete_alertNo check listed here called it with a valid call.
list_indicator_alertsNo check listed here called it with a valid call.
create_indicator_alertNo check listed here called it with a valid call.
update_indicator_alertNo check listed here called it with a valid call.
delete_indicator_alertNo check listed here called it with a valid call.
get_candlesNo check listed here called it with a valid call.
list_economic_calendarNo check listed here called it with a valid call.
get_macro_seriesNo check listed here called it with a valid call.
get_macro_indicatorNo check listed here called it with a valid call.
get_market_configNo check listed here called it with a valid call.
get_fx_pair_contextNo check listed here called it with a valid call.
get_fx_currency_contextNo check listed here called it with a valid call.
get_fx_predictionsNo check listed here called it with a valid call.
get_fx_risk_sentimentNo check listed here called it with a valid call.
get_fx_documentsNo check listed here called it with a valid call.
get_fx_sync_stateNo check listed here called it with a valid call.
get_indicatorsNo check listed here called it with a valid call.
render_chartNo 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 server version (0.2.17), the same Sealmark version (1.0.1).

  1. Av0.2.17
  2. Av0.2.17
  3. Av0.2.17
  4. Av0.2.17Sealmark 1.0.0
  5. Av0.2.17Sealmark 1.0.1
  6. Av0.2.17Sealmark 1.0.1

Package facts

License
in the file LICENSE, as the package says
Latest release
0.2.17, published 20 Sep 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 0.2.17, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "aetherwealth-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@aetherwealth/mcp@0.2.17"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add aetherwealth-mcp -- npx -y "@aetherwealth/mcp@0.2.17"

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 @aetherwealth/mcp@0.2.17"

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 @aetherwealth/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.