Robin Saige we check the tools AI agents call

shiply

now.shiply/shiply

Publish any app in one call: SQL database, functions, email, and a custom domain. Flat price.

— the operator's own registry description reported

Publisher now.shiply · first seen 2026-08-12 · endpoint https://shiply.now/mcp

allow
verdict
rich-slow-solo
cluster
ok_tools
answers
114
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 114 tools legible (band A) ●, no confirmed drift in 2 probes ●; not yet checked: truth (0 runs)

Cluster rich-slow-solo · distinctiveness 0.907 (unusual). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency4494 ms
vs populationslow
protocolcurrent
authopen
Can it be used? Q4 · observed
tools114
vs populationhigh
capabilities3
harnessA
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_3056c7f0127ef15470311454 · 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.

Q1Does it answer?alive & usable — 2 probes ●evidence ↓
Q2What is it?action ● evidence ↓
Q3Can it be checked?V n/a for this kind ◐evidence ↓
Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?rich-slow-solo · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

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)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
action55changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public44serves public factstruth-checkable against a public source — the V-ladder applies in full
generative6creates contentno answer key exists; disclosure + stability checks, never truth verdicts
unclassified6not classifiable from its textTier-1 only until its tools describe themselves
computational2deterministic transformsself-checkable by re-computation and known-answer tests
retrieval-private1serves the caller's own dataoutside truth-checking is impossible BY NATURE, not by failure — the operator-invited pathway applies

Tools last seen observed

add_custom_domain add_domain add_sending_domain add_subdomain add_suppression archive_project archive_thread attach_database attach_variable check_custom_domain check_domain connect_provider contract_amend contract_draft contract_pdf contract_send contract_status create_database create_drive create_listing create_project create_test data_export_collection data_insert data_list_collections data_query delete_database delete_listing delete_site delete_variable deploy_function detach_variable drive_delete_file drive_list_files drive_put_file duplicate_site export_account feature_site forward_thread get_account_status get_analytics get_connect_status get_function get_function_logs get_project get_site get_site_access get_test_status list_complaints list_crons list_custom_domains list_databases list_domains list_drives list_inbox list_listings list_mailbox_contacts list_my_orders list_my_sales list_project_files list_projects list_secrets list_sending_domains list_site_inbox list_site_variables list_sites list_suppressions list_test_inbox_addresses list_tests list_unsubscribes list_variables list_versions mark_thread_read promote_site publish_from_drive publish_site pull_site read_thread refund_order regenerate_brief remove_cron remove_custom_domain remove_domain remove_function remove_secret remove_sending_domain remove_suppression reply_to_thread resend_confirmation resend_intake_invite restore_project rollback_site send_broadcast send_email send_mailbox_broadcast set_cron set_handle set_link set_mailbox set_primary_subdomain set_profile set_secret set_site_access set_variable site_status summarize_thread sync_dns unarchive_thread update_brief update_listing verify_claim verify_sending_domain verify_site whoami

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 checktools passingok
name is clear & specific114/114
has a description114/114
description is substantive112/114112/114
parameters are typed114/114
parameters are described113/114113/114

114 of 114 tools graded · 114 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

2025-06-18
protocol version
session model
0.1.0
server version mcp-typescript server on vercel

Capabilities: prompts resources tools

Drift observed

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

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T20:00:35Zok_tools20044942025-06-18
2026-08-12T05:35:51Zok_tools2009542025-06-18

Watch or embed this verdict

verdict badge

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/now.shiply/shiply.svg)](https://robinsaige.com/s/now.shiply/shiply)

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