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

Results / @kawacode/mcp

@kawacode/mcp

version tested 10.6.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run20 tools

Sealmark's automated test of @kawacode/mcp 10.6.0 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B). Only 3 of 20 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 6 checks, 3 passed, 1 partial 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 3 of 20 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

B
Protocol3.5/4 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 kawa-intents 0.3.0 answered; 20 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 20 tool definition(s) and serverInfo, 1 prompt(s) and 1 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
partial
57 reply(ies) show the invalid argument was used downstream
Evidence for robust-input: first 6 of 57 lines
  1. Probe get_relevant_context: every typed argument has the wrong type
    Outcome the server used the invalid argument (an upstream request was attempted with it) and that request failed: { "success": false, "error": "Could not register repository \"12345\" with Kawa Code: Muninn is not running. Please start Muninn first…
    Decided from what the server returned (response) · tool get_relevant_context
  2. Probe get_relevant_context: wrong types plus an unexpected extra argument
    Outcome the server used the invalid argument (an upstream request was attempted with it) and that request failed: { "success": false, "error": "Could not register repository \"12345\" with Kawa Code: Muninn is not running. Please start Muninn first…
    Decided from what the server returned (response) · tool get_relevant_context
  3. Probe get_relevant_context: every string argument is an object
    Outcome the server used the invalid argument (an upstream request was attempted with it) and that request failed: { "success": false, "error": "Could not register repository \"[object Object]\" with Kawa Code: Muninn is not running. Please start Mu…
    Decided from what the server returned (response) · tool get_relevant_context
  4. Probe check_active_intent: every typed argument has the wrong type
    Outcome the server used the invalid argument (an upstream request was attempted with it) and that request failed: { "success": false, "error": "Could not register repository \"12345\" with Kawa Code: Muninn is not running. Please start Muninn first…
    Decided from what the server returned (response) · tool check_active_intent
  5. Probe check_active_intent: wrong types plus an unexpected extra argument
    Outcome the server used the invalid argument (an upstream request was attempted with it) and that request failed: { "success": false, "error": "Could not register repository \"12345\" with Kawa Code: Muninn is not running. Please start Muninn first…
    Decided from what the server returned (response) · tool check_active_intent
  6. Probe check_active_intent: every string argument is an object
    Outcome the server used the invalid argument (an upstream request was attempted with it) and that request failed: { "success": false, "error": "Could not register repository \"[object Object]\" with Kawa Code: Muninn is not running. Please start Mu…
    Decided from what the server returned (response) · tool check_active_intent
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 102 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

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
n/a
no tool declares readOnlyHint: true
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
pass
list_team_intents, log_work, infer_history 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
get_relevant_contextNo check listed here called it with a valid call.
check_active_intentNo check listed here called it with a valid call.
create_and_activate_intentNo check listed here called it with a valid call.
activate_intentNo check listed here called it with a valid call.
resume_intentNo check listed here called it with a valid call.
get_intents_for_fileNo check listed here called it with a valid call.
list_team_intentsNone
complete_intentNo check listed here called it with a valid call.
update_intentNo check listed here called it with a valid call.
log_workNone
record_decisionNo check listed here called it with a valid call.
get_session_decisionsNo check listed here called it with a valid call.
get_project_decisionsNo check listed here called it with a valid call.
get_decision_detailNo check listed here called it with a valid call.
edit_session_decisionNo check listed here called it with a valid call.
detect_intent_conflictsNo check listed here called it with a valid call.
infer_historyNone
get_resolution_contextNo check listed here called it with a valid call.None
arbiter_resolveNo check listed here called it with a valid call.None
arbiter_applyNo check listed here called it with a valid call.None

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

  1. Bv10.1.1Sealmark 1.0.0
  2. Bv10.6.0Sealmark 1.0.1
  3. Bv10.6.0Sealmark 1.0.1

Package facts

License
in the file LICENSE, as the package says
Latest release
10.6.0, published 14 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 10.6.0, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "kawacode-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@kawacode/mcp@10.6.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add kawacode-mcp -- npx -y "@kawacode/mcp@10.6.0"

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 @kawacode/mcp@10.6.0"

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 @kawacode/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.