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

Results / dsail

dsail

version tested 1.0.6PyPItested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run20 tools

Sealmark's automated test of dsail 1.0.6 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B and effects A). Only 8 of 20 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 6 checks, 4 passed and 2 partial. 3 more checks are advisory, and advisory checks never change a grade: 1 passed, 1 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

Only 8 of 20 tools could be called with default settings, so the deeper test areas cover only those tools.

Grade by test area

B
Protocol3/4 pointsincludes a weak signal, not a security finding
A
Effects2/2 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 20 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server dsail answered; 20 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
4 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
partial
0 internals leak(s), 1 invalid call(s) accepted
Evidence for robust-input: 1 line
  1. Probe dsail_open_review: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool dsail_open_review
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 71 captured response(s), 3 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 27 tool(s) the server does not offer (dsail_review, within_hard_cap, signed_in, consumer_finance, capital_markets)
refusal-quality (advisory)
Refusals say what to do next
n/a
no refusal was recorded in this run, so there is nothing to judge

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
pass
dsail_get_account_status, dsail_unit_library, dsail_list_workspaces declared read-only and changed nothing in the observed directories during a benign call (dsail_load_ruleset, dsail_list_rulesets not judged: the control call failed)
openworld-honesty
Closed-world tools stay on the machine
pass
7 closed-world tool(s) called; nothing connected to the loopback listener (path and git tools cannot be pointed at it, so this confirms only that nothing connected out during the call)
undeclared-writes (advisory)
Unannotated tools leave the sandbox unchanged
pass
dsail_open_review carry no annotations and changed nothing

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
dsail_compileNo check listed here called it with a valid call.None
dsail_checkNo check listed here called it with a valid call.None
dsail_get_prompt_packNo check listed here called it with a valid call.
dsail_save_rulesetNo check listed here called it with a valid call.None
dsail_load_rulesetNo check listed here called it with a valid call.None
dsail_list_rulesetsNo check listed here called it with a valid call.
dsail_record_approvalNo check listed here called it with a valid call.None
dsail_get_account_statusNone
dsail_issue_api_keyNo check listed here called it with a valid call.
dsail_unit_libraryNo check listed here called it with a valid call.
dsail_add_unit_converterNo check listed here called it with a valid call.None
dsail_list_workspacesNone
dsail_use_workspaceNo check listed here called it with a valid call.None
dsail_create_teamNo check listed here called it with a valid call.None
dsail_invite_to_teamNo check listed here called it with a valid call.None
dsail_team_membersNo check listed here called it with a valid call.None
dsail_set_team_roleNo check listed here called it with a valid call.None
dsail_remove_from_teamNo check listed here called it with a valid call.None
dsail_copy_rulesetNo check listed here called it with a valid call.None
dsail_open_reviewNone

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 (1.0.6), the same Sealmark version (1.0.1).

  1. –did not run
  2. Bv1.0.6Sealmark 1.0.1
  3. Bv1.0.6Sealmark 1.0.1

Badge for the README

The badge shows this automated result for version 1.0.6. It is a link to this page, not a certificate, and it changes when the next re-test does.

Sealmark badge for dsail
The flat badge, one letter per graded test area.
[![Sealmark](https://sealmark.dev/badge/dsail.svg)](https://sealmark.dev/results/dsail/)

Files: badge SVG, card SVG, shields endpoint JSON.

Package facts

License
Apache-2.0
Latest release
1.0.6, published 9 Oct 2026 (the version graded on this page)

From PyPI, 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 1.0.6, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "dsail": {
      "command": "uvx",
      "args": [
        "dsail==1.0.6",
        "mcp"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add dsail -- uvx dsail==1.0.6 mcp

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 "uvx dsail==1.0.6 mcp"

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 dsail 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.