Robin Saige we check the tools AI agents call

CryptoData API

io.github.elevasyncsolutions-jpg/cryptodata-api

Crypto MCP with 21 tools for market data, DeFi, analytics, and sentiment. Post-paid USDC billing.

— the operator's own registry description reported

Publisher io.github.elevasyncsolutions-jpg · first seen 2026-08-12 · endpoint https://cryptodata-api.datachain.workers.dev/mcp

allow
verdict
stale-rich-slow-solo
cluster
ok_tools
answers
48
tools served

Dependency rating derived

allow
allow — alive & usable · retrieval-public ● · V2 has a twin ◐
allow — because answers ●, 48 tools legible (band B) ●, no confirmed drift in 2 probes ●; not yet checked: truth (0 runs)

Cluster stale-rich-slow-solo · distinctiveness 0.561 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency462 ms
vs populationslow
protocolbehind
authopen
Can it be used? Q4 · observed
tools48
vs populationhigh
capabilities2
harnessB
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_03f645109aa6ad704f699f1c · 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?V2 has a twin ◐evidence ↓
Q4Did it hold?harness B · truth not yet run · no drift ●evidence ↓
Q5What company does it keep?stale-rich-slow-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-public36serves public factstruth-checkable against a public source — the V-ladder applies in full
action6changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
unclassified5not classifiable from its textTier-1 only until its tools describe themselves
computational1deterministic transformsself-checkable by re-computation and known-answer tests

Tools last seen observed

analyze_contract analyze_solana_token check_agent_balance check_approvals check_usage compare_coins delete_alert get_alerts get_arbitrage get_categories get_coin get_defi_pools get_defi_protocol get_defi_tvl get_defi_yields get_exchanges get_fear_greed get_gas get_gas_all get_global get_jupiter_quote get_liquidations get_meme_analyze get_meme_scan get_meme_trending get_network_health get_ohlc get_portfolio_health get_portfolio_value get_price get_price_summary get_pump_fun_new get_search get_social_sentiment get_stablecoins get_summary get_token_holders get_top get_top_gainers get_top_losers get_top_volume get_trending get_whale_moves market_correlation pay_agent register set_price_alert trending_categories

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 B — usable, with rough edges.

legibility checktools passingok
name is clear & specific48/48
has a description48/48
description is substantive38/4838/48
parameters are typed48/48
parameters are described5/485/48

48 of 48 tools graded · 48 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
3.0.0
server version CryptoData API

Capabilities: logging 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
2026-08-14T19:59:31Zok_tools2004622025-03-26
2026-08-12T05:34:44Zok_tools2003912025-03-26

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/io.github.elevasyncsolutions-jpg/cryptodata-api.svg)](https://robinsaige.com/s/io.github.elevasyncsolutions-jpg/cryptodata-api)

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