nft-wash-trading-detector

imeunk89/nft-wash-trading-detector
★ 1 stars Python AI/LLM Updated today
Memory-driven market-surveillance agent that detects NFT wash-trading rings and gets sharper with every confirmed case — CockroachDB vector memory + Managed MCP Server, AWS Bedrock
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "nft-wash-trading-det": {
      "command": "uvx",
      "args": [
        "nft-wash-trading-detector"
      ]
    }
  }
}

Or install with pip: pip install nft-wash-trading-detector

README Excerpt

A memory-driven agent that detects NFT wash trading and **learns to catch it earlier over time**. When a wash-trading wallet pair is confirmed, the agent doesn't just log the pattern — it traces back through the wallet's full history to mine the *earliest precursor signals* that preceded the obvious round-tripping, and stores them as a growing **playbook** in CockroachDB. Each confirmed case makes the next detection earlier and sharper.

Topics

agentic-memoryaws-bedrockcockroachdbmarket-surveillancenftwash-trading