ThirdMade Shelf
net.thirdmade/shelf
26 pay-per-call tools for agents: scrape, verify, guards, crypto. x402 USDC on Base.
— the operator's own registry description reported
Publisher net.thirdmade · first seen 2026-08-31 · endpoint https://shelf.thirdmade.net/mcp
Dependency rating derived
allow — alive & usable · kind unknown · V n/a
Cluster mid-solo · distinctiveness 0.418 (moderate). Every figure is a percentile or class within the 15,472-server census — see the whole spectrum.
🔏 Signed receipt rr_7318c13097ba828c935178bb · 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.
● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →
History observed
Every probe we made, oldest → newest (1 shown, 2026-09-06 → 2026-09-06). 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 |
|---|---|---|
| 2026-09-06 | outcome | first 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 →):
| nature | tools | meaning | what checking applies |
|---|---|---|---|
| unclassified | 16 | not classifiable from its text | Tier-1 only until its tools describe themselves |
| retrieval-public | 6 | serves public facts | truth-checkable against a public source — the V-ladder applies in full |
| generative | 2 | creates content | no answer key exists; disclosure + stability checks, never truth verdicts |
| action | 1 | changes the world | no true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions |
| orchestration | 1 | routes other tools | identity + fronted-service disclosure checks (gateway vs costume) |
Tools last seen observed
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 | 26/26 | ✓ |
| has a description | 26/26 | ✓ |
| description is substantive | 26/26 | ✓ |
| parameters are typed | 26/26 | ✓ |
| parameters are described | 26/26 | ✓ |
26 of 26 tools graded · 26 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
Capabilities: resources tools
Drift observed
No confirmed drift on record. Baseline set 2026-09-06; changes appear here after human review.
raw probe records
| probed (UTC) | outcome | http | ms | protocol |
|---|---|---|---|---|
| 2026-09-06T06:17:55Z | ok_tools | 200 | 94 | 2025-06-18 |
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:
[](https://robinsaige.com/s/net.thirdmade/shelf)
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.
Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →