Connect AgentFlow and your agent gets 6 tools, among them agent_pulse, counterparty_risk, index_stats. It answers at https://agentflow.watch/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
Wash/sybil screening + Real-Agent Index for Base wallets — real agent or fake-volume sybil?
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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_risk | Counterparty risk score (0-100; LOW/MEDIUM/HIGH/UNKNOWN) for any Base wallet — wash + hub detection + automation score + known-entity labels. Inputs: address |
index_stats | AgentFlow coverage stats: wallets tracked, agents labeled, hubs excluded, authorized x402 payers, transfers in the live window, last indexed block. |
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_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. Inputs: address |
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 |
Every block below points at https://agentflow.watch/mcp. Pick your client and copy.
claude mcp add --transport http agentflow https://agentflow.watch/mcp
{
"mcpServers": {
"agentflow": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agentflow.watch/mcp"]
}
}
}{
"mcpServers": {
"agentflow": {
"url": "https://agentflow.watch/mcp"
}
}
}{
"servers": {
"agentflow": {
"type": "http",
"url": "https://agentflow.watch/mcp"
}
}
}{
"context_servers": {
"agentflow": {
"url": "https://agentflow.watch/mcp"
}
}
}{
"mcpServers": {
"agentflow": {
"serverUrl": "https://agentflow.watch/mcp"
}
}
}{
"mcpServers": {
"agentflow": {
"url": "https://agentflow.watch/mcp"
}
}
}name: AgentFlow
version: 0.0.1
schema: v1
mcpServers:
- name: AgentFlow
type: streamable-http
url: https://agentflow.watch/mcp{
"mcpServers": {
"agentflow": {
"httpUrl": "https://agentflow.watch/mcp"
}
}
}{
"mcpServers": {
"agentflow": {
"type": "http",
"url": "https://agentflow.watch/mcp"
}
}
}{
"mcpServers": {
"agentflow": {
"url": "https://agentflow.watch/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fagentflow.watch%2Fmcp&type=streamable_http&id=agentflow&name=AgentFlow
It answered our last check on 22 October 2026 in 221 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
6, as returned by the server's own tools/list on 15 September 2026: agent_pulse, counterparty_risk, index_stats, real_agent_index, screen_wallet, x402_rail_tape.
It answered our last check on 22 October 2026 in 221 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentflow.watch/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.leonidahqadmin-cell. Endpoint host: agentflow.watch. ARD identifier: urn:air:io.github.leonidahqadmin-cell:mcp:agentflow.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.