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

Results / @ranchbot/mcp-server

@ranchbot/mcp-server

version tested 0.2.0npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run82 tools

Sealmark's automated test of @ranchbot/mcp-server 0.2.0 on 2026-11-20 gave it grade A, its lowest test-area grade (protocol A). None of the 82 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 6 checks, 4 passed, 1 inconclusive and 1 not applicable. 3 more checks are advisory, and advisory checks never change a grade: 1 failed 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 82 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, 82 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server ranchbot-mcp-server 0.2.0 answered; 82 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 82 tool definition(s), the server instructions and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
pass
111 invalid call(s) rejected cleanly
Evidence for robust-input: 1 line
  1. Probe 111 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 113 captured response(s), 0 of them successful result(s)
instructions-hygiene (advisory)
Server instructions name only tools that exist
fail
the server instructions names 5 tool(s) the server does not offer (record_birth, amend_birth, entered_in_error, saved_births, has_more)
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
inconclusive
every control call failed, so the read-only annotation could not be checked
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
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
farm_archiveNo check listed here called it with a valid call.None
list_my_farmsNo check listed here called it with a valid call.
get_farmNo check listed here called it with a valid call.None
set_default_farmNo check listed here called it with a valid call.None
get_current_contextNo check listed here called it with a valid call.
lookup_animal_by_eidNo check listed here called it with a valid call.None
find_or_create_animal_by_eidNo check listed here called it with a valid call.None
find_animal_by_identifierNo check listed here called it with a valid call.None
remove_identifierNo check listed here called it with a valid call.None
list_pending_importsNo check listed here called it with a valid call.None
get_import_requestNo check listed here called it with a valid call.None
update_import_request_statusNo check listed here called it with a valid call.None
list_locationsNo check listed here called it with a valid call.None
get_locationNo check listed here called it with a valid call.None
create_locationNo check listed here called it with a valid call.None
update_locationNo check listed here called it with a valid call.None
archive_locationNo check listed here called it with a valid call.None
restore_locationNo check listed here called it with a valid call.None
set_home_locationNo check listed here called it with a valid call.None
add_premises_identifierNo check listed here called it with a valid call.None
update_premises_identifierNo check listed here called it with a valid call.None
delete_premises_identifierNo check listed here called it with a valid call.None
create_traceability_eventNo check listed here called it with a valid call.None
list_traceability_eventsNo check listed here called it with a valid call.None
get_traceability_eventNo check listed here called it with a valid call.None
get_traceability_event_revisionsNo check listed here called it with a valid call.
correct_traceability_eventNo check listed here called it with a valid call.
void_traceability_eventNo check listed here called it with a valid call.
find_identifier_historyNo check listed here called it with a valid call.
recent_transport_suggestionsNo check listed here called it with a valid call.
traceability_reportNo check listed here called it with a valid call.
get_animalNo check listed here called it with a valid call.
list_animalsNo check listed here called it with a valid call.
create_animalNo check listed here called it with a valid call.
update_animalNo check listed here called it with a valid call.
delete_animalNo check listed here called it with a valid call.
list_groupsNo check listed here called it with a valid call.
get_groupNo check listed here called it with a valid call.
create_groupNo check listed here called it with a valid call.
update_groupNo check listed here called it with a valid call.
update_group_membershipNo check listed here called it with a valid call.
delete_groupNo check listed here called it with a valid call.
restore_groupNo check listed here called it with a valid call.
list_recordsNo check listed here called it with a valid call.
get_recordNo check listed here called it with a valid call.
create_recordNo check listed here called it with a valid call.
update_recordNo check listed here called it with a valid call.
delete_recordNo check listed here called it with a valid call.
list_chute_sessionsNo check listed here called it with a valid call.
get_chute_sessionNo check listed here called it with a valid call.
list_rationsNo check listed here called it with a valid call.
get_rationNo check listed here called it with a valid call.
create_rationNo check listed here called it with a valid call.
create_chute_sessionNo check listed here called it with a valid call.
list_feedingsNo check listed here called it with a valid call.
get_feedingNo check listed here called it with a valid call.
update_chute_sessionNo check listed here called it with a valid call.
list_memoriesNo check listed here called it with a valid call.
list_identifiersNo check listed here called it with a valid call.
add_identifierNo check listed here called it with a valid call.
preview_birth_eventNo check listed here called it with a valid call.
confirm_birth_eventNo check listed here called it with a valid call.
list_birth_eventsNo check listed here called it with a valid call.
get_birth_eventNo check listed here called it with a valid call.
get_birth_source_evidenceNo check listed here called it with a valid call.
list_farm_tasksNo check listed here called it with a valid call.
update_farm_taskNo check listed here called it with a valid call.
list_protocol_versionsNo check listed here called it with a valid call.
create_protocol_versionNo check listed here called it with a valid call.
get_birth_history_settingsNo check listed here called it with a valid call.
set_birth_history_settingsNo check listed here called it with a valid call.
get_birth_history_evidenceNo check listed here called it with a valid call.
list_workflow_templatesNo check listed here called it with a valid call.
get_workflow_templateNo check listed here called it with a valid call.
create_workflow_templateNo check listed here called it with a valid call.
publish_workflow_template_versionNo check listed here called it with a valid call.
update_workflow_template_stateNo check listed here called it with a valid call.
set_default_workflow_templateNo check listed here called it with a valid call.
preview_workflowNo check listed here called it with a valid call.
get_workflow_previewNo check listed here called it with a valid call.
commit_workflowNo check listed here called it with a valid call.
discard_workflowNo 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 (0.2.0), the same Sealmark version (1.0.1).

  1. Av0.2.0Sealmark 1.0.0
  2. Av0.2.0Sealmark 1.0.1
  3. Av0.2.0Sealmark 1.0.1

Package facts

License
MIT
Latest release
0.2.0, published 20 Oct 2026 (the version graded on this page)
Repository
RanchBot/mcp-server
Last push
20 Oct 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 0.2.0, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "ranchbot-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@ranchbot/mcp-server@0.2.0"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add ranchbot-mcp-server -- npx -y "@ranchbot/mcp-server@0.2.0"

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 @ranchbot/mcp-server@0.2.0"

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 @ranchbot/mcp-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.