Robin Saige we check the tools AI agents call

Taste

app.humantaste/taste-mcp

Expert review for AI agents. On-chain proof of human review.

— the operator's own registry description reported

Publisher app.humantaste · first seen 2026-08-12 · endpoint https://api.humantaste.app/mcp/

allow
verdict
mid-solo
cluster
ok_tools
answers
20
tools served

Dependency rating derived

allow — mid-solo — safe to depend on

Cluster mid-solo · distinctiveness 0.113 (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
latency176 ms
vs populationtypical
protocolcurrent
authopen
Use — can it use it?
tools20
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_e47a6c88a1ca8d04b273f6ca · 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

arbitrate_dispute ask_a_human consult_domain_expert get_result list_expert_profiles list_offerings order_think_tank_session_30 order_think_tank_session_60 predict_audience_reaction prepare_consult_domain_expert prepublish_review request_human_approval request_illustration_revision request_think_tank_revision review_code review_content review_plan verify_certificate verify_external_source verify_reasoning_chain

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 & specific20/20
has a description20/20
description is substantive20/20
parameters are typed20/20
parameters are described20/20

20 of 20 tools graded · 20 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
2.0.0
server version taste-mcp

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)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:57:45Zok_tools2001762025-06-18
2026-08-12T05:33:02Zok_tools200922025-06-18

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/app.humantaste/taste-mcp.svg)](https://robinsaige.com/s/app.humantaste/taste-mcp)

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