Sealmark
Automated re-test on 2026-11-22: not checked by hand, and not yet reviewed by the maintainers.

Results / @shiplightai/mcp

@shiplightai/mcp

version tested 0.2.4npmtested 2026-11-22Sealmark 1.0.1methodology 0.3-draftSTANDARD run12 tools

Sealmark's automated test of @shiplightai/mcp 0.2.4 on 2026-11-22 gave it grade B, its lowest test-area grade (protocol B). None of the 12 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 10 checks, 3 passed, 1 partial, 2 inconclusive and 4 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

None of the 12 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, 12 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server shiplight-mcp 1.0.0 answered; 12 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 12 tool definition(s) and serverInfo, 1 prompt(s) and 1 resource(s), including parameter text: nothing suspicious
robust-input
Survives malformed tool input
partial
0 internals leak(s), 1 invalid call(s) accepted
Evidence for robust-input: 1 line
  1. Probe close_session: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool close_session
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 57 captured response(s), 1 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
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
n/a
no unannotated read-style tool could be given a harness-owned control argument

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
new_sessionNo check listed here called it with a valid call.
save_storage_stateNo check listed here called it with a valid call.
close_sessionNo check listed here called it with a valid call.None
navigateNo check listed here called it with a valid call.
get_page_infoNo check listed here called it with a valid call.None
inspect_pageNo check listed here called it with a valid call.None
actNo check listed here called it with a valid call.None
get_locatorsNo check listed here called it with a valid call.None
get_browser_console_logsNo check listed here called it with a valid call.None
get_browser_network_logsNo check listed here called it with a valid call.None
generate_html_reportNo check listed here called it with a valid call.
attach_to_browserNo check listed here called it with a valid call.None

What was not covered

Grade over time

Since the run on

  • Server version changed from 0.2.3 to 0.2.4.

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

  1. Bv0.2.3Sealmark 1.0.0
  2. Bv0.2.3Sealmark 1.0.1
  3. Bv0.2.3Sealmark 1.0.1
  4. Bv0.2.4Sealmark 1.0.1

Package facts

License
MIT
Latest release
0.2.3, published 28 Sep 2026. This page graded 0.2.4.
Repository
ShiplightAI/shiplight-cli
Last push
29 Sep 2026
Open issues and pull requests
0

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

{
  "mcpServers": {
    "shiplightai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@shiplightai/mcp@0.2.4"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add shiplightai-mcp -- npx -y "@shiplightai/mcp@0.2.4"

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 @shiplightai/mcp@0.2.4"

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 @shiplightai/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.