Radar sample scorecard
First sightings across the latest N published snapshots, grouped by original verdict and compared to current quotes. Missing outcomes stay null; observed liquidity below $100 is reported separately; holding periods vary
Input
Sample response
Published by the provider. Your run returns a fresh response.
response10 keys
at"2026-08-12T10:00:00.000Z"
chain"base"
cohorts5 keys
caution{ count, liquidityGone, medianChangePct, … }5 keys
clear{ count, liquidityGone, medianChangePct, … }5 keys
high-risk{ count, liquidityGone, medianChangePct, … }5 keys
insufficient-data{ count, liquidityGone, medianChangePct, … }5 keys
unassessed{ count, liquidityGone, medianChangePct, … }5 keys
coverage15 keys
completefalse
missingSnapshotDates[…]0 items
note"Published radar samples with variable holding periods; missing quotes are not losses."
poolsObserved1
poolsWithoutSafety0
poolsWithoutToken0
priceBatchesFailed0
requestedDays7
snapshotsListed7
snapshotsLoaded7
tokensObserved1
tokensPriced0
windowBasis"latest-published-snapshots"
windowFirstSnapshot"2026-08-06"
windowLastSnapshot"2026-08-12"
disclaimer"A track record, not investment advice."
methodology"First sightings in published samples; current deepest observed pool. liquidityGone is null when unavailable; true only for observed liquidity below $100. Medians use available quotes and varying holding periods."
provenance4 keys
commit"https://github.com/tevfikefeaydin/agenttoll/commit/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
index"https://raw.githubusercontent.com/tevfikefeaydin/agenttoll/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/data/scout/index.json"
integrity"Git revision pins the published bytes. A payment transaction does not authenticate a snapshot hash or its capture time."
revision"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
tokens1 item
0{ flaggedOn, liquidityGone, liquidityNowUsd, … }9 keys
trackRecord3 keys
daysCovered7
firstSnapshot"2026-08-06"
lastSnapshot"2026-08-12"
windowDays7
responseobject, 10 keysYour agent can do this on its own
Add the MCP URL in Claude Code, Cursor or Codex. Your agent can run Tools within its spending limits, or ask for approval each time. Connect your agent
Connect your agent
Add one MCP URL and your agent can find and run this tool within its spending limits. Choose “Ask each time” if you want to approve every Call.
MCP URL
https://app.aecon.ai/mcpTerminalbash
In Claude Code, open /mcp, select agentic-economy, then choose Authenticate.
Track record
- Paid calls, last 30 days
- 3
- Buyers, last 30 days
- 3
- Last paid call
Reported by the x402 directory.