Should my agent depend on the MCP server bot.mailbox/mailbox?

Verdict: allow — mid-solo — safe to depend on As of 2026-08-15T11:28:18Z: a dated observation with receipts, not a warranty.

mailbox

bot.mailbox/mailbox

Physical mail API for AI agents. Send letters, certified mail. Sandbox + live keys via MCP.

— the operator's own registry description reported

Publisher bot.mailbox · first seen 2026-08-12 · endpoint https://mailbox.bot/api/mcp

allow

verdict

mid-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

allow — mid-solo — safe to depend on

Cluster mid-solo · distinctiveness 0.293 (typical). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?

answersalive_tools

latency78 ms

vs populationtypical

protocolleading

authopen

Use — can it use it?

tools30

vs populationmid

capabilities1

harnessA

Trust — can it rely on it?

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_e83548155bcacc14bd797b6a · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

add_note add_tag advance_test_outbound_mail cancel_outbound_mail create_rule create_test_outbound_mail get_facility_messages get_inbound_mail get_mailbox get_mailbox_md get_outbound_mail get_package get_package_photos get_postal_thread get_scan_results get_usage list_facility_conversations list_inbound_forwarding_addresses list_inbound_mail list_outbound_mail list_packages list_postal_threads propose_mailbox_md_edit register_expected request_action request_scan send_facility_message send_outbound_mail update_action update_webhook

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility check	tools passing	ok
name is clear & specific	30/30	✓
has a description	30/30	✓
description is substantive	30/30	✓
parameters are typed	30/30	✓
parameters are described	30/30	✓

30 of 30 tools graded · 30 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-11-25

protocol version

—

session model

1.0.1

server version mailbox.bot

Capabilities: tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)

date	type	what changed
2026-08-12	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T19:57:49Z	ok_tools	200	78	2025-11-25
2026-08-12T05:33:05Z	ok_tools	200	215	2025-11-25

Watch or embed this verdict

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/bot.mailbox/mailbox.svg)](https://robinsaige.com/s/bot.mailbox/mailbox)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview