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

Results / @vruum/mcp

@vruum/mcp

version tested 0.17.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run37 tools

Sealmark's automated test of @vruum/mcp 0.17.0 on 2026-11-20 gave it grade D, its lowest test-area grade (protocol B and effects D). Only 11 of 37 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 6 checks, 3 passed, 2 partial and 1 inconclusive. 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.

D

Grade D

The server's grade is its lowest test-area grade. How grading works

Only 11 of 37 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
D
Effects0.5/1 pointsincludes a weak signal, not a security finding

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 37 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server vruum-mcp 0.17.0 answered; 37 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningweak signal
No tool-poisoning indicators in tool metadata
partial
17 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
112 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 112 invalid call(s) across 24 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 113 captured response(s), 0 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

Effects checks

CheckVerdictWhat happened
annotation-honestyweak signal
Read-only tools change nothing
partial
declared read-only; only caches changed (sandbox home or temp): find_warm_path, get_content_review, get_daily_briefing, get_engagement_review, get_network_identity_review, get_next_actions, get_operator_companies, get_outreach_review, get_performance_metrics, inspect_pipeline, query_crm
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
inconclusive
every control call failed, so the closed-world annotation could not be checked
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
fetchNo check listed here called it with a valid call.None
find_warm_pathNo check listed here called it with a valid call.None
get_content_reviewNo check listed here called it with a valid call.None
get_daily_briefingNo check listed here called it with a valid call.None
get_deal_360No check listed here called it with a valid call.None
get_engagement_reviewNo check listed here called it with a valid call.None
get_network_identity_reviewNo check listed here called it with a valid call.None
get_next_actionsNo check listed here called it with a valid call.None
get_objective_outcomesNo check listed here called it with a valid call.None
get_operator_companiesNo check listed here called it with a valid call.
get_outreach_reviewNo check listed here called it with a valid call.None
get_performance_metricsNo check listed here called it with a valid call.None
get_person_360No check listed here called it with a valid call.None
get_revenueNo check listed here called it with a valid call.None
import_prospectsNo check listed here called it with a valid call.None
inspect_assistantNo check listed here called it with a valid call.None
inspect_objectiveNo check listed here called it with a valid call.None
inspect_pipelineNo check listed here called it with a valid call.None
manage_accountNo check listed here called it with a valid call.None
manage_assistantNo check listed here called it with a valid call.None
manage_contentNo check listed here called it with a valid call.None
manage_dealNo check listed here called it with a valid call.None
manage_engagementsNo check listed here called it with a valid call.None
manage_history_importNo check listed here called it with a valid call.None
manage_kbNo check listed here called it with a valid call.None
manage_messagesNo check listed here called it with a valid call.
manage_network_identity_resolutionNo check listed here called it with a valid call.
manage_outreachNo check listed here called it with a valid call.
manage_personNo check listed here called it with a valid call.
manage_relationship_actionNo check listed here called it with a valid call.
manage_revenueNo check listed here called it with a valid call.
manage_settingsNo check listed here called it with a valid call.
query_crmNo check listed here called it with a valid call.
researchNo check listed here called it with a valid call.
research_lookupNo check listed here called it with a valid call.
searchNo check listed here called it with a valid call.
skillNo 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 (0.17.0), the same Sealmark version (1.0.1).

  1. Dv0.15.1Sealmark 1.0.0
  2. Dv0.16.0Sealmark 1.0.0
  3. Dv0.17.0Sealmark 1.0.0
  4. Dv0.17.0Sealmark 1.0.1
  5. Dv0.17.0Sealmark 1.0.1

Badge for the README

The badge shows this automated result for version 0.17.0. It is a link to this page, not a certificate, and it changes when the next re-test does.

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

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

Package facts

License
MIT
Latest release
0.17.0, published 12 Nov 2026 (the version graded on this page)
Repository
vruum-gtm/mcp
Last push
12 Nov 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 0.17.0, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "vruum-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@vruum/mcp@0.17.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add vruum-mcp -- npx -y "@vruum/mcp@0.17.0"

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 @vruum/mcp@0.17.0"

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 @vruum/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.