AgentFlow MCP Server

by leonidahqadmin-cell Your server? Claim it

answering

AgentFlow is answering right now. Last checked 2 min ago. It exposes 6 tools.

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

Uptime history 91 days of history · worst day 95%

91 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

275 ms

Response time

average over 24h

open, no key

Access

streamable-http

Nothing serious here today

Today is the operative word: we check AgentFlow every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agentflow --transport http https://agentflow.watch/mcp

Settings → Connectors → Add custom connector, then paste this address

https://agentflow.watch/mcp

~/.codex/config.toml

[mcp_servers.agentflow]
url = "https://agentflow.watch/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agentflow": {
      "url": "https://agentflow.watch/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agentflow": {
      "type": "http",
      "url": "https://agentflow.watch/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent

agent_pulse

The speedometer: distinct genuine AI agents ACTIVE on Base in the live 24h / 72h window (rises AND falls), vs. the cumulative count.

counterparty

counterparty_risk

Counterparty risk score (0-100; LOW/MEDIUM/HIGH/UNKNOWN) for any Base wallet — wash + hub detection + automation score + known-entity labels.

index

index_stats

AgentFlow coverage stats: wallets tracked, agents labeled, hubs excluded, authorized x402 payers, transfers in the live window, last indexed block.

real

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.

screen

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 trusts or pays a counterparty.

x402

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, share of value >=$1, and chain coverage %. Methodology-versioned, receipts-backed. NOT total x402 volume — a lower bound with its blind spots disclosed.

Endpoints

URL	Transport	State	Latency	Checked
https://agentflow.watch/mcp	streamable-http	answering	324 ms	2 min ago

Alternatives to AgentFlow

same job, measured the same way

Djd Agent Score

by jacobsd32-cpu

Reputation scoring for AI agent wallets on Base. Trust scores, fraud checks, x402.

55 installs/wk local only

Spawnpay

by robocular

Crypto wallets, payments, and referral earnings for AI agents on Base L2

75 installs/wk local only

Everything File Search

by elis132

Lightning-fast Windows file search for AI agents via voidtools Everything's real-time NTFS index

251 installs/wk local only

Rubric MCP

by 0xsims

Attested evidence tools for AI agents: sanctions screening, agent/wallet records, paid via x402.

local only

MintwareDevelopers

by mintwaredevelopers

Look up on-chain Attribution reputation scores for wallets and AI agents on Base.

55 installs/wk local only

Global Intel Exchange

by joseph-ceo

Real-time sanctions screening, CVE, and company registry checks for agents.

65 installs/wk local only

Screenshotor

by screenshotor

Website screenshots for AI agents: real Chrome, ad/cookie/chat blocking, bot-wall detection.

51 installs/wk answering

PayPerScreen

by tonythetiger22

Sanctions, crypto wallet, email and IP screening for agents. Pay per check in USDC via x402.

132 installs/wk local only

AgentFlow — questions

Answers built from our own checks of this server.

What can AgentFlow do?

It exposes 6 tools, read directly from the server on our last check. Among them: agent_pulse, counterparty_risk, index_stats, real_agent_index, screen_wallet, x402_rail_tape. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is AgentFlow working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 275 ms. The bar chart above shows every period we have measured.

How do I connect AgentFlow?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does AgentFlow need an API key?

No. AgentFlow completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is AgentFlow?

It answers our handshake in 275 ms on average, which is faster than 50% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.