Robin Saige we check the tools AI agents call

AgentServices

to.agentservices/agentservices

52 paid x402 API endpoints for AI agents — crypto, data, DeFi, market intelligence.

— the operator's own registry description reported

Publisher to.agentservices · first seen 2026-08-12 · endpoint https://agentservices.to/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
40
tools served

Dependency rating derived

allow
allow — alive & usable · retrieval-public ● · V3 has answer key ◐
allow — because answers ●, 40 tools legible (band A) ●, no confirmed drift in 2 probes ●; not yet checked: truth (0 runs)

Cluster rich-solo · distinctiveness 0.369 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency207 ms
vs populationtypical
protocolleading
authopen
Can it be used? Q4 · observed
tools40
vs populationhigh
capabilities2
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_80631876d6d5a1c46c0392fe · 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?retrieval-public ● evidence ↓
Q3Can it be checked?V3 has answer key ◐evidence ↓
Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?rich-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
retrieval-public34serves public factstruth-checkable against a public source — the V-ladder applies in full
generative3creates contentno answer key exists; disclosure + stability checks, never truth verdicts
computational1deterministic transformsself-checkable by re-computation and known-answer tests
orchestration1routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)
unclassified1not classifiable from its textTier-1 only until its tools describe themselves

Tools last seen observed

agent_context arbitrage_scanner chat commodities correlation_matrix crypto_prices crypto_signals deep_research defi_strategy defi_tvl defi_yields exchange_flows fear_greed fx_rates generate_image github_velocity ip_geolocation liquidation_map list_policies llm_inference macro_indicators market_pulse marketing_ad_copy marketing_sentiment marketing_trends onchain_overview package_security portfolio_intelligence resolve_dispute sec_filings seo_keywords stablecoin_flows stock_history stock_quote technical_indicators text_to_speech token_risk url_metadata web_extract whale_tracking

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 & specific40/40
has a description40/40
description is substantive40/40
parameters are typed40/40
parameters are described34/4034/40

40 of 40 tools graded · 40 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

2026-07-28
protocol version
session model
5.3.0
server version AgentServices

Capabilities: 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
2026-08-14T20:00:46Zok_tools2002072026-07-28
2026-08-12T05:35:59Zok_tools200992026-07-28

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/to.agentservices/agentservices.svg)](https://robinsaige.com/s/to.agentservices/agentservices)

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