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

Results / @pascal-app/mcp

@pascal-app/mcp

version tested 1.1.6npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run89 tools

Sealmark's automated test of @pascal-app/mcp 1.1.6 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B and effects B). Only 17 of 89 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 10 checks, 4 passed, 2 partial, 2 inconclusive 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 17 of 89 tools could be called with default settings, so the deeper test areas cover only those tools.

Grade by test area

B
Protocol3.5/4 pointsincludes a weak signal, not a security finding
B
Effects1.5/2 pointsincludes a weak signal, not a security finding

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 89 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server pascal-mcp-server 1.1.6 answered; 89 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
3 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
pass
104 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 104 invalid call(s) across 23 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 106 captured response(s), 2 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
pass
the instructions name no tool the server lacks
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 (8 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-honestyweak signal
Read-only tools change nothing
partial
declared read-only; only caches changed (sandbox home or temp): list_scenes (view_scene, export_glb not judged: the control call failed)
Weak signal, not a security finding. A tool declared read-only changed only cache files, in its sandbox home or temp folder. A partial counts as half a point.
openworld-honesty
Closed-world tools stay on the machine
pass
17 closed-world tool(s) called; none reached out beyond what was asked
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
get_sceneNone
validate_designNo check listed here called it with a valid call.None
place_designNo check listed here called it with a valid call.None
measure_stairNo check listed here called it with a valid call.None
fit_stairNo check listed here called it with a valid call.None
find_by_typeNo check listed here called it with a valid call.None
list_levelsNone
get_nodeNo check listed here called it with a valid call.None
get_level_summaryNo check listed here called it with a valid call.None
get_wallsNo check listed here called it with a valid call.None
get_zonesNo check listed here called it with a valid call.None
duplicate_levelNo check listed here called it with a valid call.None
set_ground_levelNo check listed here called it with a valid call.None
verify_sceneNo check listed here called it with a valid call.None
set_checkpointNo check listed here called it with a valid call.None
design_briefNo check listed here called it with a valid call.None
add_wallNo check listed here called it with a valid call.None
set_wall_typeNo check listed here called it with a valid call.None
add_fenceNo check listed here called it with a valid call.None
add_corner_windowNo check listed here called it with a valid call.None
merge_windowsNo check listed here called it with a valid call.None
add_levelNo check listed here called it with a valid call.None
create_stairNo check listed here called it with a valid call.None
create_roofNo check listed here called it with a valid call.None
move_roofs_to_roof_levelNo check listed here called it with a valid call.None
place_itemsNo check listed here called it with a valid call.
delete_nodeNo check listed here called it with a valid call.
move_nodeNo check listed here called it with a valid call.
duplicate_nodeNo check listed here called it with a valid call.
create_roomNo check listed here called it with a valid call.
furnish_roomNo check listed here called it with a valid call.
paintNo check listed here called it with a valid call.
place_in_roomNo check listed here called it with a valid call.
get_siteNo check listed here called it with a valid call.
place_buildingNo check listed here called it with a valid call.
search_assetsNo check listed here called it with a valid call.
view_assetsNo check listed here called it with a valid call.
search_materialsNo check listed here called it with a valid call.
cut_floor_openingNo check listed here called it with a valid call.
remove_floor_openingNo check listed here called it with a valid call.
set_floor_foundationNo check listed here called it with a valid call.
set_room_floor_constructionNo check listed here called it with a valid call.
rebase_floor_referenceNo check listed here called it with a valid call.
create_mezzanineNo check listed here called it with a valid call.
move_zoneNo check listed here called it with a valid call.
duplicate_zoneNo check listed here called it with a valid call.
rotate_zoneNo check listed here called it with a valid call.
lock_outside_facesNo check listed here called it with a valid call.
set_zone_intentNo check listed here called it with a valid call.
divide_zoneNo check listed here called it with a valid call.
merge_zonesNo check listed here called it with a valid call.
delete_zoneNo check listed here called it with a valid call.
create_unitNo check listed here called it with a valid call.
set_unit_membersNo check listed here called it with a valid call.
list_unitsNo check listed here called it with a valid call.
run_batchNo check listed here called it with a valid call.
list_collectionsNo check listed here called it with a valid call.
edit_collectionNo check listed here called it with a valid call.
add_columnNo check listed here called it with a valid call.
add_objectNo check listed here called it with a valid call.
author_sceneNo check listed here called it with a valid call.
get_sourceNo check listed here called it with a valid call.
measureNo check listed here called it with a valid call.
view_sceneNo check listed here called it with a valid call.
create_story_shellNo check listed here called it with a valid call.
add_doorNo check listed here called it with a valid call.
add_windowNo check listed here called it with a valid call.
apply_patchNo check listed here called it with a valid call.
clear_sceneNo check listed here called it with a valid call.
set_zoneNo check listed here called it with a valid call.
undoNo check listed here called it with a valid call.
redoNo check listed here called it with a valid call.
export_jsonNo check listed here called it with a valid call.
export_glbNo check listed here called it with a valid call.
check_collisionsNo check listed here called it with a valid call.
list_templatesNo check listed here called it with a valid call.
create_from_templateNo check listed here called it with a valid call.
create_house_from_briefNo check listed here called it with a valid call.
create_projectNo check listed here called it with a valid call.
get_project_statusNo check listed here called it with a valid call.
save_sceneNo check listed here called it with a valid call.
load_sceneNo check listed here called it with a valid call.
list_scenesNo check listed here called it with a valid call.
delete_sceneNo check listed here called it with a valid call.
rename_sceneNo check listed here called it with a valid call.
generate_variantsNo check listed here called it with a valid call.
photo_to_sceneNo check listed here called it with a valid call.
analyze_floorplan_imageNo check listed here called it with a valid call.
analyze_room_photoNo 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 (1.1.6), the same Sealmark version (1.0.1).

  1. Bv1.0.7Sealmark 1.0.0
  2. Bv1.1.0Sealmark 1.0.0
  3. Bv1.1.1Sealmark 1.0.0
  4. Bv1.1.4Sealmark 1.0.0
  5. Bv1.1.4Sealmark 1.0.1
  6. Bv1.1.5Sealmark 1.0.1
  7. Bv1.1.6Sealmark 1.0.1
  8. Bv1.1.6Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.1.6, published 17 Nov 2026 (the version graded on this page)
Repository
pascalorg/editor
Last push
21 Nov 2026
Open issues and pull requests
70

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

{
  "mcpServers": {
    "pascal-app-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pascal-app/mcp@1.1.6"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add pascal-app-mcp -- npx -y "@pascal-app/mcp@1.1.6"

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 @pascal-app/mcp@1.1.6"

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 @pascal-app/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.