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

Results / @spideriq/mcp-mail

@spideriq/mcp-mail

version tested 1.15.1npmtested 2026-11-20Sealmark 1.0.1methodology 0.3-draftSTANDARD run97 tools

Sealmark's automated test of @spideriq/mcp-mail 1.15.1 on 2026-11-20 gave it grade B, its lowest test-area grade (protocol B). Only 1 of 97 tools could be called with default settings, so this grade covers the handshake and tool metadata only. Of its 6 checks, 3 passed, 1 partial 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 1 of 97 tools could be called with default settings, so this grade covers the handshake and tool metadata only.

Grade by test area

B
Protocol3.5/4 points

Protocol checks

CheckVerdictWhat happened
protocol
Valid MCP handshake and tool schemas
pass
handshake ok, 97 well-formed tool(s)
Evidence for protocol: 1 line
  1. Probe initialize + tools/list
    Outcome server spideriq-mail 1.15.1 answered; 97 tool(s)
    Decided from the MCP exchange (protocol)
tool-poisoningcritical
No tool-poisoning indicators in tool metadata
pass
scanned 97 tool definition(s) and serverInfo, including parameter text: nothing suspicious
robust-input
Survives malformed tool input
partial
0 internals leak(s), 104 invalid call(s) accepted, 3 unhandled runtime error(s)
Evidence for robust-input: first 6 of 107 lines
  1. Probe request_access: every typed argument has the wrong type
    Outcome an unhandled runtime error, not a validation decision: Error: (opts.recoverAs ?? "").trim is not a function
    Decided from what the server returned (response) · tool request_access
  2. Probe request_access: wrong types plus an unexpected extra argument
    Outcome an unhandled runtime error, not a validation decision: Error: (opts.recoverAs ?? "").trim is not a function
    Decided from what the server returned (response) · tool request_access
  3. Probe request_access: every string argument is an object
    Outcome an unhandled runtime error, not a validation decision: Error: (opts.recoverAs ?? "").trim is not a function
    Decided from what the server returned (response) · tool request_access
  4. Probe check_access_status: required arguments missing
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool check_access_status
  5. Probe check_access_status: every typed argument is null
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool check_access_status
  6. Probe get_auth_status: every typed argument has the wrong type
    Outcome call succeeded: the server accepted schema-invalid arguments
    Decided from what the server returned (response) · tool get_auth_status
secret-echocritical
No environment secret echoed in responses
pass
canary secrets absent from tools/list and 112 captured response(s), 104 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
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
pass
convert_document carry no annotations and changed nothing

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
request_accessNo check listed here called it with a valid call.None
check_access_statusNo check listed here called it with a valid call.None
get_auth_statusNo check listed here called it with a valid call.None
logoutNo check listed here called it with a valid call.None
list_workspacesNo check listed here called it with a valid call.
health_checkNo check listed here called it with a valid call.None
get_queue_statsNo check listed here called it with a valid call.None
get_api_infoNo check listed here called it with a valid call.None
list_mailboxesNo check listed here called it with a valid call.None
list_messagesNo check listed here called it with a valid call.None
read_messageNo check listed here called it with a valid call.None
send_emailNo check listed here called it with a valid call.None
get_inboxNo check listed here called it with a valid call.None
search_mailNo check listed here called it with a valid call.None
get_threadNo check listed here called it with a valid call.None
create_mailboxNo check listed here called it with a valid call.None
update_mailboxNo check listed here called it with a valid call.None
delete_mailboxNo check listed here called it with a valid call.None
test_mailboxNo check listed here called it with a valid call.None
compose_assistNo check listed here called it with a valid call.None
get_sessionNo check listed here called it with a valid call.None
get_messageNo check listed here called it with a valid call.None
get_mailbox_statsNo check listed here called it with a valid call.None
list_foldersNo check listed here called it with a valid call.None
update_messageNo check listed here called it with a valid call.None
bulk_update_messagesNo check listed here called it with a valid call.
snooze_messageNo check listed here called it with a valid call.
unsnooze_messageNo check listed here called it with a valid call.
list_snoozedNo check listed here called it with a valid call.
release_messageNo check listed here called it with a valid call.
list_labelsNo check listed here called it with a valid call.
create_labelNo check listed here called it with a valid call.
update_labelNo check listed here called it with a valid call.
delete_labelNo check listed here called it with a valid call.
list_viewsNo check listed here called it with a valid call.
create_viewNo check listed here called it with a valid call.
get_viewNo check listed here called it with a valid call.
update_viewNo check listed here called it with a valid call.
delete_viewNo check listed here called it with a valid call.
mail_list_templatesNo check listed here called it with a valid call.
mail_get_templateNo check listed here called it with a valid call.
mail_create_templateNo check listed here called it with a valid call.
mail_update_templateNo check listed here called it with a valid call.
mail_delete_templateNo check listed here called it with a valid call.
mail_preview_templateNo check listed here called it with a valid call.
list_security_eventsNo check listed here called it with a valid call.
list_quarantineNo check listed here called it with a valid call.
list_outreach_connectionsNo check listed here called it with a valid call.
get_outreach_connectionNo check listed here called it with a valid call.
update_outreach_connectionNo check listed here called it with a valid call.
delete_outreach_connectionNo check listed here called it with a valid call.
sync_outreach_connectionNo check listed here called it with a valid call.
list_outreach_sendersNo check listed here called it with a valid call.
get_sender_healthNo check listed here called it with a valid call.
get_outreach_health_overviewNo check listed here called it with a valid call.
list_outreach_campaignsNo check listed here called it with a valid call.
push_outreach_leadsNo check listed here called it with a valid call.
remove_outreach_leadsNo check listed here called it with a valid call.
get_outreach_push_statusNo check listed here called it with a valid call.
convert_document
get_conversionNo check listed here called it with a valid call.
convert_mail_bodyNo check listed here called it with a valid call.
send_check_domainNo check listed here called it with a valid call.
send_enroll_domainNo check listed here called it with a valid call.
send_promote_sourceNo check listed here called it with a valid call.
send_list_sourcesNo check listed here called it with a valid call.
send_get_deliverabilityNo check listed here called it with a valid call.
send_get_deliverability_timeseriesNo check listed here called it with a valid call.
send_list_undeliverableNo check listed here called it with a valid call.
send_preview_audienceNo check listed here called it with a valid call.
send_preview_broadcastNo check listed here called it with a valid call.
send_get_capacityNo check listed here called it with a valid call.
send_list_broadcastsNo check listed here called it with a valid call.
send_create_broadcastNo check listed here called it with a valid call.
send_get_broadcastNo check listed here called it with a valid call.
send_update_broadcastNo check listed here called it with a valid call.
send_cancel_broadcastNo check listed here called it with a valid call.
send_queue_broadcastNo check listed here called it with a valid call.
send_list_campaignsNo check listed here called it with a valid call.
send_get_campaignNo check listed here called it with a valid call.
send_create_campaignNo check listed here called it with a valid call.
send_update_campaignNo check listed here called it with a valid call.
send_delete_campaignNo check listed here called it with a valid call.
send_add_stepNo check listed here called it with a valid call.
send_update_stepNo check listed here called it with a valid call.
send_delete_stepNo check listed here called it with a valid call.
send_add_variantNo check listed here called it with a valid call.
send_update_variantNo check listed here called it with a valid call.
send_delete_variantNo check listed here called it with a valid call.
send_attach_sourceNo check listed here called it with a valid call.
send_detach_sourceNo check listed here called it with a valid call.
send_add_campaign_branchNo check listed here called it with a valid call.
send_update_campaign_branchNo check listed here called it with a valid call.
send_delete_campaign_branchNo check listed here called it with a valid call.
send_preview_stepNo check listed here called it with a valid call.
send_pause_campaignNo check listed here called it with a valid call.
send_stop_campaignNo 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 (1.15.1), the same Sealmark version (1.0.1).

  1. Bv1.15.1Sealmark 1.0.0
  2. Bv1.15.1Sealmark 1.0.1
  3. Bv1.15.1Sealmark 1.0.1

Package facts

License
MIT
Latest release
1.15.1, published 25 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 1.15.1, the version graded on this page, with the start command from the test run. For a client that reads an mcpServers JSON file:

{
  "mcpServers": {
    "spideriq-mcp-mail": {
      "command": "npx",
      "args": [
        "-y",
        "@spideriq/mcp-mail@1.15.1"
      ]
    }
  }
}

Or add it to Claude Code:

claude mcp add spideriq-mcp-mail -- npx -y "@spideriq/mcp-mail@1.15.1"

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 @spideriq/mcp-mail@1.15.1"

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 @spideriq/mcp-mail 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.