Robin Saige we check the tools AI agents call

Grabblist

com.grabbitapp/grabblist

Save and organize web finds in persistent, user-controlled collections for AI assistants.

— the operator's own registry description reported

Publisher com.grabbitapp · first seen 2026-08-14 · endpoint https://mcp.grabbitapp.com/api/mcp

allow
verdict
stale-mid-solo
cluster
ok_tools
answers
23
tools served

Dependency rating derived

allow — stale-mid-solo — safe to depend on

Cluster stale-mid-solo · distinctiveness 0.128 (typical). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency172 ms
vs populationtypical
protocolbehind
authopen
Use — can it use it?
tools23
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_eb94637f6fa065dc22b23521 · 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_item add_to_collection ask_agent create_collection delete_collection delete_item get_collection_activity get_item get_item_graph get_item_history get_wishlist link_items list_collections ping remove_from_collection restore_item search_saved send_feedback set_pinned_items unlink_items update_collection update_item update_price

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 & specific23/23
has a description23/23
description is substantive22/2322/23
parameters are typed23/23
parameters are described23/23

23 of 23 tools graded · 23 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

2025-03-26
protocol version
session model
2.1.0
server version Grabblist

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 (1 shown, 2026-08-14 → 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
2026-08-14outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:58:11Zok_tools2001722025-03-26

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/com.grabbitapp/grabblist.svg)](https://robinsaige.com/s/com.grabbitapp/grabblist)

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