AgentFlow

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

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

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

    How to connect

    How to connect AgentFlow to Claude

    The server address to paste into Claude settings:

    https://agentflow.watch/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect AgentFlow to ChatGPT

    The server address to paste into ChatGPT settings:

    https://agentflow.watch/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect AgentFlow to Cursor

    The server address to paste into Cursor settings:

    https://agentflow.watch/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (6)

    Raw names from tools/list. Only developers need these.

    screen_walletWash/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.
    counterparty_riskCounterparty risk score (0-100; LOW/MEDIUM/HIGH/UNKNOWN) for any Base wallet — wash + hub detection + automation score + known-entity labels.
    real_agent_indexThe Real-Agent Index: what % of 'AI agent' USDC flow on Base is wash/self-dealing vs. genuine one-way payments. The honest benchmark.
    agent_pulseThe speedometer: distinct genuine AI agents ACTIVE on Base in the live 24h / 72h window (rises AND falls), vs. the cumulative count.
    index_statsAgentFlow coverage stats: wallets tracked, agents labeled, hubs excluded, authorized x402 payers, transfers in the live window, last indexed block.
    x402_rail_tapeThe 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.