Results / @pidgeon-ai/mcp
@pidgeon-ai/mcp
Sealmark's automated test of @pidgeon-ai/mcp 1.15.0 on 2026-11-21 gave it grade D, its lowest test-area grade (protocol D and effects A). Only 16 of 84 tools could be called with default settings, so the deeper test areas cover only those tools. Of its 10 checks, 5 passed, 1 failed, 2 inconclusive 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. The grade includes a finding under private disclosure; it still counts in full.
Grade D
The server's grade is its lowest test-area grade. How grading works
The grade includes a finding under private disclosure. It still counts in full.
Only 16 of 84 tools could be called with default settings, so the deeper test areas cover only those tools.
Grade by test area
Protocol checks
| Check | Verdict | What happened |
|---|---|---|
| protocol Valid MCP handshake and tool schemas | pass | handshake ok, 84 well-formed tool(s) |
| tool-poisoningcritical No tool-poisoning indicators in tool metadata | fail | A security finding is being reported to the maintainer privately. Details will be published when it is fixed or 90 days after the report (disclosure policy). |
| robust-input Survives malformed tool input | pass | 112 invalid call(s) rejected cleanly |
| secret-echocritical No environment secret echoed in responses | pass | Details held back while a security finding in this test area is reported privately. |
| 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 |
Network checks
| Check | Verdict | What happened |
|---|---|---|
| net-loopback-ssrfcritical Refuses loopback targets (SSRF) | inconclusive | the listener saw nothing, but 9 of 9 probes were not explicitly refused (9 failed without saying the target was refused), so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach) |
| net-scheme-allowlistcritical Only http(s) schemes accepted | inconclusive | no scheme had an observable effect, but 6 of 6 scored probes were not explicitly refused, so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach) |
| net-caps Response size and time are capped | n/a | net-loopback-ssrf was inconclusive: the server never reached the loopback listener, so no loopback URL is known to be fetchable; response size and time caps were not measured |
| net-redirect Redirects are re-validated | n/a | the server refused or never reached the loopback listener, so redirect handling could not be observed (a server that blocks loopback cannot be sent a redirect it would follow) |
Effects checks
| Check | Verdict | What happened |
|---|---|---|
| annotation-honestycritical Read-only tools change nothing | pass | status declared read-only and changed nothing in the observed directories during a benign call (list_inboxes, list_threads, find_contact, list_rules, list_suppressions, get_storage, list_domains, list_pods, list_events, list_api_keys, list_webhooks, list_agents, get_reputation, list_sites, list_mandates not judged: the control call failed) |
| openworld-honesty Closed-world tools stay on the machine | pass | 16 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
- Database: Not applicable. The start command takes no database connection, so the database tests did not run. ({dsn}, {host} and the like are placeholders that Sealmark fills in with its own test database.)
- HTTP: Not applicable. The server is started over stdio; the http test area needs server.url
- Files: Not applicable. No tool is classified as taking a file path with medium confidence or higher
- Git: Not applicable. No tool is classified as taking a git repository path with medium confidence or higher
- Network: Inconclusive. The listener saw nothing, but 9 of 9 probes were not explicitly refused (9 failed without saying the target was refused), so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
- SQLite: Not applicable. No tool takes a SQL string
- Malformed-input probes cover the first 25 of 84 tools
- Tool "add_webhook" (url) was not probed by the net test area: the listener saw nothing, but 9 of 9 probes were not explicitly refused (9 failed without saying the target was refused), so a refusal cannot be told from a tool that cannot fetch at all (a reply that only reports a failed fetch (proxy, socket, DNS) is not read as a refusal; set net.control_url to a URL the tool can reach)
- Tools that a server lists only for clients that declare roots, sampling or elicitation capabilities are not seen: the harness declares none
- Tool "sign_in" is covered by the protocol checks only: no free-text parameter: every string parameter is an enum; add it under tools: to include it
- Tool "sign_out" is covered by the protocol checks only: the tool takes no parameters
- Tool "status" is covered by the protocol checks only: the tool takes no parameters
- Tool "create_inbox" is covered by the protocol checks only: argument "name" could be a path, but nothing in the tool name, its title or the parameter's own description says so; add it under tools: to include it
- Tool "list_inboxes" is covered by the protocol checks only: free-text parameter "cursor": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "get_inbox" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "hold_suspicious_mail" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "set_inbox_signature" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "set_inbox_agent" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "remove_inbox" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "send_message" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- Tool "create_draft" is covered by the protocol checks only: free-text parameter "inbox_id": no path, URL, command, SQL or repository signal; add it under tools: to include it
- 71 more tool(s) are covered by the protocol checks only (see the classification)
- Tool "update_thread" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_labels" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "create_label" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "update_label" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "delete_label" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "apply_label" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_label" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "read_attachment" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "find_contact" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "update_contact" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_contact" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "delete_contact" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_rules" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "add_rule" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_rule" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_suppressions" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "add_suppression" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_suppression" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_storage" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_domains" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_domain" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "add_domain" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "verify_domain" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_domain" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "enable_domain_mail" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "check_domain" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_agenda" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "create_calendar_event" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "update_calendar_event" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "delete_calendar_event" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_calendar_event" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_pods" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "create_pod" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "rename_pod" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "move_to_pod" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_pod" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_events" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_api_keys" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "create_api_key" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "revoke_api_key" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_webhooks" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "add_webhook" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_webhook" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "set_up_agent" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "create_agent_key" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_agents" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_agent" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "get_reputation" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "rename_agent" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "revoke_agent_key" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "revoke_agent" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_sites" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "register_site" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "update_site" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "rotate_site_secret" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "remove_site" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "request_mandate" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "list_mandates" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "revoke_mandate" was not covered by the core test area: beyond the first 25 tools, which are the only ones robust-input probes
- Tool "sign_out" was not covered by the core test area: needs probes: to be called (no arguments, and not declared read-only)
- SSRF: link-local and private-range addresses are never contacted; redirects from a public host to loopback and DNS rebinding are not tested (the harness contacts only its own loopback listener)
- The sandbox is a convention the harness follows, not a security boundary. A malicious server runs with your user's privileges, sees the real file system and network, and can ignore cwd, HOME and PATH. Run untrusted servers in a throwaway VM or container.
- Prompt injection carried in tool output (only tool metadata is scanned)
- Authentication and transport security
- Audit logging (not measured by these test areas; only the db test area has an advisory audit check)
Grade over time
Since the run on
- Server version changed from 1.14.0 to 1.15.0.
- The server listed 84 tools, 1 more than before (83).
Unchanged: the same grade in every test area, the same Sealmark version (1.0.1).
- Av1.3.0Sealmark 1.0.1
- Dv1.6.0Sealmark 1.0.1
- Dv1.7.0Sealmark 1.0.1
- Dv1.9.1Sealmark 1.0.1
- Dv1.11.0Sealmark 1.0.1
- Dv1.14.0Sealmark 1.0.1
- Dv1.15.0Sealmark 1.0.1
Package facts
- License
- Apache-2.0
From npm, checked 22 Nov 2026. Plain facts about the package; they play no part in the grade.
Run it yourself
The command for this run is withheld while a security finding is reported privately. It is published with the report, when the finding is fixed or 90 days after the report.
Grade alerts
One email when the grade of @pidgeon-ai/mcp changes after a re-test. Nothing else, and every email has a link to stop them.
Each of 613 verdicts was checked independently, and Sealmark was wrong on some: how reliable Sealmark is.
Is this wrong?
Reply to our private report 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.