Robin Saige we check the tools AI agents call

Hex Pm

io.github.pipeworx-io/hex-pm

Hex.pm MCP — package registry for the Elixir & Erlang ecosystems.

— the operator's own registry description reported

Publisher io.github.pipeworx-io · first seen 2026-08-12 · endpoint https://gateway.pipeworx.io/hex-pm/mcp

warn
verdict
farm-costume
cluster
ok_tools
answers
31
tools served

Dependency rating derived

warn — farm-costume — usable, but look before you lean on it

Cluster farm-costume · distinctiveness 0.559 (moderate). 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
latency61 ms
vs populationfast
protocolcurrent
authopen
Use — can it use it?
tools31
vs populationmid
capabilities3
harnessA
Trust — can it rely on it?
identityfarm_member
servers on its host1312
verifiabilityunassessed
duplicate inventoryyes
drift events0
answers trueno primary

🔏 Signed receipt rr_007bbc999870a8e69c7143f2 · 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.

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
retrieval-public16serves public factstruth-checkable against a public source — the V-ladder applies in full
action4changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
predictive4claims about the futurescoreable only in retrospect — the archive scores yesterday's predictions against today's outcome
computational3deterministic transformsself-checkable by re-computation and known-answer tests
generative2creates contentno answer key exists; disclosure + stability checks, never truth verdicts
orchestration2routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)

Tools last seen

ai_visibility_check ask_pipeworx ask_pipeworx_beta ask_pipeworx_grounded bet_research compare_entities deep_research discover_tools entity_profile forget generate_llms_txt list_subscriptions pipeworx_feedback pipeworx_trending polymarket_arbitrage polymarket_edge_tracker polymarket_edges polymarket_fill_risk polymarket_kalshi_spread recall recent_alerts recent_changes remember resolve_entity scan_competitor_ai_presence scan_dependency search_within subscribe suggest_questions unsubscribe validate_claim

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 & specific31/31
has a description31/31
description is substantive31/31
parameters are typed31/31
parameters are described31/31

31 of 31 tools graded · 31 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 pipeworx-gateway

Capabilities: prompts resources 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
2026-08-14T20:00:03Zok_tools200612025-06-18
2026-08-12T05:35:17Zok_tools200502025-06-18

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/io.github.pipeworx-io/hex-pm.svg)](https://robinsaige.com/s/io.github.pipeworx-io/hex-pm)

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