LeashIndex Get the report

Index / messaging

mailbox.bot

bot-mailbox-mailbox declares 47 capabilities across 47 tools, with 2 critical issues.

92/100 exposureHigh exposure

Manifest recorded 2026-10-21 from tools/list on https://mailbox.bot/api/mcp, published in the official MCP registry as bot.mailbox/mailbox 1.0.3. The date changes only when the manifest does. Not verified by a maintainer.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 47 tools

47 of 47 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 8 of 47 tools

8 tools are classified as irreversible and declare no limit.

high · no-expiry · All 47 tools

47 of 47 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 47 tools

47 of 47 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 10 of 47 tools

10 tools can modify data and declare no limit.

low · uncapped-read · 29 of 47 tools

29 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
get_mailboxread declared
get_usageread declared
list_inbound_forwarding_addressesread declared
list_inbound_mailread declared
get_inbound_mailread declared
list_postal_threadsread declared
get_postal_threadread declared
get_mailbox_mdread declared
propose_mailbox_md_editwrite inferred
send_facility_messagesend inferred
list_facility_conversationsread declared
get_facility_messagesread declared
update_webhookwrite inferred
send_outbound_maildestructive declared
list_outbound_mailread declared
get_outbound_mailread declared
cancel_outbound_maildestructive declared
create_test_outbound_mailsend inferred
advance_test_outbound_mailsend inferred
list_agent_inboxread declared
get_agent_inbox_contextread declared
get_agent_inbox_sourcesread declared
list_agent_inbox_scansread declared
get_agent_inbox_scanread declared
get_agent_inbox_activityread declared
report_agent_inbox_outcomewrite assumed
get_agent_inbox_handlingread declared
propose_agent_inbox_handlingwrite assumed
seed_agent_inbox_sandboxwrite assumed
list_webhook_endpointsread declared
create_webhook_endpointwrite inferred
update_webhook_endpointdestructive declared
test_webhook_endpointwrite assumed
test_webhook_endpoint_with_samplewrite assumed
rotate_webhook_endpoint_secretdestructive declared
list_webhook_deliveriesread declared
replay_webhook_deliverywrite assumed
list_inbound_itemsread declared
get_inbound_item_sourcesread declared
search_inbound_itemsread declared
get_inbound_itemread declared
get_inbound_pagesread declared
quote_inbound_forwardread declared
request_inbound_actionwrite inferred
get_inbound_activityread declared
quote_outbound_mailread declared
send_text_letterdestructive declared

Record history

Earlier records for this server. A correction is added here, never written over the record it corrects.

RecordedExposureSource
2026-10-1692 tools/list on https://mailbox.bot/api/mcp, published in the official MCP registry as bot.mailbox/mailbox 1.0.3
2026-10-1190 tools/list on https://mailbox.bot/api/mcp, published in the official MCP registry as bot.mailbox/mailbox 1.0.2
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.