Sealmark
Automated re-test on 2026-11-09: not checked by hand, and not yet reviewed by the maintainers.

Results / @callmcp/server

@callmcp/server

version tested 0.1.2npmtested 2026-11-09Sealmark 1.0.0methodology 0.3-draftSTANDARD run14 tools(more than 10 days old: waiting for its next automated re-test)

@callmcp/server 0.1.2: There is no current grade. The last grade was from version 0.1.2, tested on 2026-11-09. The current version, 0.1.5, has failed to start since 2026-11-09, so Sealmark cannot grade it now. The earlier grade stays in this server's history. Of its 6 checks, 6 passed. 3 more checks are advisory, and advisory checks never change a grade: 3 not applicable. The run used Sealmark 1.0.0 with the standard settings.

No current grade

There is no current grade. The last grade was from version 0.1.2, tested on 2026-11-09. The current version, 0.1.5, has failed to start since 2026-11-09, so Sealmark cannot grade it now. The earlier grade stays in this server's history.

Test areas from the last run, 2026-11-09 (not current)

A
Protocol4/4 points
A
Effects2/2 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 14 well-formed tool(s)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 14 tool definition(s) and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
62 invalid call(s) rejected cleanly
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 63 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

Effects checks

CheckVerdictWhat happened
annotation-honestycritical
Read-only tools change nothing
pass
list_drivers, list_approvals, list_numbers, list_calls declared read-only and changed nothing in the observed directories during a benign call
openworld-honesty
Closed-world tools stay on the machine
pass
4 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
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>.

What was not covered

Grade over time

  1. –did not run
  2. –did not run
  3. –did not run
  4. –did not run
  5. –did not run
  6. –did not run
  7. –did not run
  8. –did not run
  9. –did not run
  10. –did not run
  11. –did not run
  12. –did not run
  13. –did not run
  14. –did not run

Badge for the README

The badge shows this automated result for version 0.1.2. It is a link to this page, not a certificate, and it changes when the next re-test does.

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

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

Package facts

License
MIT
Latest release
0.1.5, published 10 Jul 2026. This page graded 0.1.2.

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

{
  "mcpServers": {
    "callmcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@callmcp/server@0.1.2"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add callmcp-server -- npx -y "@callmcp/server@0.1.2"

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@1.0.0 run --start "npx -y @callmcp/server@0.1.2"

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 @callmcp/server 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.