MCP serverio.github.leonidahqadmin-cell/agentflow

Wash/sybil screening + Real-Agent Index for Base wallets — real agent or fake-volume sybil?

UNRATEDActivestreamable-httpagentflow.watch

Overview

Score?

UNRATED 0.710

of what a free look can see, on 32 looks

Looks

last 14 hr ago

Tools

URL

agentflow.watch/mcp

streamable-http

Says it is

agentflow 1.0.0

protocol 2025-06-18

In the record since

32 days ago

0median 0.606 · this server 0.710 · highest on record 0.8561

The tools this server lists, read out of the definition it returned
Tool	Schema
agent_pulse The speedometer: distinct genuine AI agents ACTIVE on Base in the live 24h / 72h window (rises AND falls), vs. the cumulative count.	input · no output
counterparty_risk Counterparty risk score (0-100; LOW/MEDIUM/HIGH/UNKNOWN) for any Base wallet — wash + hub detection + automation score + known-entity labels.	input · no output
index_stats AgentFlow coverage stats: wallets tracked, agents labeled, hubs excluded, authorized x402 payers, transfers in the live window, last indexed block.	input · no output
real_agent_index The Real-Agent Index: what % of 'AI agent' USDC flow on Base is wash/self-dealing vs. genuine one-way payments. The honest benchmark.	input · no output
screen_wallet Wash/sybil screen for any Base wallet — real autonomous agent or fake-volume sybil? Returns a calibrated sybil_score (0-100), confidence, and the reasons. Use before an agent trust	input · no output
x402_rail_tape The Base EIP-3009 Settlement Tape: daily verifiable FLOOR on gasless x402-style USDC settlement on Base — tx count, volume, wash-suspect share (count + value), median payment, shar	input · no output

Verify it yourselfnpx teppi-check https://agentflow.watch/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2GDTC27D7KAA9SB45A2D