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

Results / telbase

telbase

version tested 1.0.8npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run45 tools

Sealmark's automated test of telbase 1.0.8 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). None of the 45 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 6 checks, 4 passed 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.

A

Grade A

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

None of the 45 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

A
Protocol4/4 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 45 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server telbase 0.1.0 answered; 45 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 45 tool definition(s), the server instructions and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
108 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 108 invalid call(s) across 22 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 108 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-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
add_custom_domainNo check listed here called it with a valid call.None
cancel_deployNo check listed here called it with a valid call.None
check_app_healthNo check listed here called it with a valid call.
connect_githubNo check listed here called it with a valid call.
delete_env_varNo check listed here called it with a valid call.None
delete_projectNo check listed here called it with a valid call.None
enable_database_extensionNo check listed here called it with a valid call.None
get_account_statusNo check listed here called it with a valid call.
get_appNo check listed here called it with a valid call.None
get_app_logsNo check listed here called it with a valid call.None
get_database_infoNo check listed here called it with a valid call.None
get_deploy_logsNo check listed here called it with a valid call.None
get_deploy_statusNo check listed here called it with a valid call.None
get_github_statusNo check listed here called it with a valid call.None
get_job_executionsNo check listed here called it with a valid call.None
get_projectNo check listed here called it with a valid call.None
get_sessionNo check listed here called it with a valid call.None
get_storage_credentialsNo check listed here called it with a valid call.None
get_storage_infoNo check listed here called it with a valid call.None
invite_memberNo check listed here called it with a valid call.None
list_appsNo check listed here called it with a valid call.
list_custom_domainsNo check listed here called it with a valid call.None
list_deploysNo check listed here called it with a valid call.None
list_env_varsNo check listed here called it with a valid call.None
list_orgsNo check listed here called it with a valid call.
list_projectsNo check listed here called it with a valid call.
list_rollback_targetsNo check listed here called it with a valid call.
list_teamNo check listed here called it with a valid call.
pause_jobNo check listed here called it with a valid call.
protect_appNo check listed here called it with a valid call.
register_appNo check listed here called it with a valid call.
remove_custom_domainNo check listed here called it with a valid call.
reset_serviceNo check listed here called it with a valid call.
restart_serviceNo check listed here called it with a valid call.
resume_jobNo check listed here called it with a valid call.
resume_serviceNo check listed here called it with a valid call.
rollback_deployNo check listed here called it with a valid call.
run_scheduled_jobNo check listed here called it with a valid call.
set_env_varsNo check listed here called it with a valid call.
suspend_serviceNo check listed here called it with a valid call.
switch_orgNo check listed here called it with a valid call.
toggle_auto_deployNo check listed here called it with a valid call.
update_projectNo check listed here called it with a valid call.
update_scheduleNo check listed here called it with a valid call.
verify_custom_domainNo 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 (1.0.8), the same Sealmark version (1.0.1).

  1. –did not run
  2. Av0.14.0-beta.2Sealmark 1.0.1
  3. Av1.0.8Sealmark 1.0.1
  4. Av1.0.8Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.0.8, published 27 Oct 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 1.0.8, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "telbase": {
      "command": "npx",
      "args": [
        "-y",
        "telbase@1.0.8",
        "mcp",
        "serve"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add telbase -- npx -y "telbase@1.0.8" mcp serve

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 telbase@1.0.8 mcp serve"

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 telbase 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.