• HIGH RISK
  • SUSPICIOUS
  • CLEAN
  • MANUAL

How to detect fraudulent accounts with your AI

Connect Shumei Anti-Fraud to your agent. Once connected, your AI can scan device and network data to flag bad actors.

Ask AI about this page

Short answer

How can I find bot accounts with my AI?

Your AI uses Shumei Anti-Fraud to check device IDs and IP addresses for signs of automation or fraud. It flags suspicious users and bot clusters so you can act. You'll see the risk breakdown below.

Risk outcomes.

Where fraud signals land.

The AI sorts every check into specific risk categories.

HIGH RISK

Bot farm alerts

The AI finds groups of accounts using the same device ID or IP. These are flagged as coordinated attacks.

SUSPICIOUS

Anomalous users

Individual accounts with weird device fingerprints get flagged for your review.

CLEAN

Verified users

Accounts with standard device and network data are marked as low risk.

MANUAL

Human review needed

If the device data is conflicting, the AI leaves the final decision to you.

The workflow

What your AI does when a user signs up.

The AI acts as a gatekeeper by checking technical fingerprints.

  1. Scan device data

    The AI pulls device IDs and hardware fingerprints to look for bot patterns.

    check_device_risk

  2. Analyze IP origin

    It checks the IP address to see if the user is using a proxy or a suspicious data center.

    check_device_risk

  3. Identify clusters

    The AI looks for multiple accounts tied to a single device to catch bot farms.

    check_device_risk

  4. Flag for review

    The AI summarizes the risk level and presents the suspicious accounts to you.

    check_device_risk

Try it

Copy these to start.

Use these prompts to begin your fraud investigation.

Starting points

Replace the bracketed text with your specific user lists or log files.

Shumei Anti-Fraud Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_NphjwTgTckqznjJKJ8hhvrWSClPg0QUpBWBQpHXH/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Shumei Anti-Fraud capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "shumei-anti-fraud-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_NphjwTgTckqznjJKJ8hhvrWSClPg0QUpBWBQpHXH/mcp"
    }
  }
}
Copy into chat04

  • Check the device risk for the users in this CSV file.

  • Are there any bot farms active in my recent signup logs?

  • Scan these IP addresses for suspicious activity.

  • Flag any accounts in my database that share a device ID.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Shumei Anti-Fraud once, then ask.

Link the MCP to your client. Your credentials stay encrypted, and you can start asking questions immediately.

Connect Shumei Anti-Fraud to your AI

FAQ

How this task behaves

  • 01

    Can the AI automatically ban users?

    No. The AI identifies and flags suspicious accounts, but you must decide whether to ban them.

  • 02

    Does it check email addresses?

    No. This tool focuses on device IDs and IP addresses to find hardware-level fraud.

  • 03

    How does it find bot farms?

    It looks for multiple accounts that share the same device ID or originate from the same suspicious IP.

  • 04

    Will it delete my user data?

    No. The AI only reads the data to perform risk checks; it cannot delete or modify your database.

  • 05

    Can I use this with any AI client?

    Yes, as long as your client is MCP-compatible, like Claude, Cursor, or Windsurf.

  • More questions about Shumei Anti-Fraud? The Connector page answers them. See everything the Shumei Anti-Fraud Connector can do

Connect Shumei Anti-Fraud to Claude, Cursor, ChatGPT & more