The Behavioural Prediction MCP Server provides AI-powered tools to analyze wallet behaviour prediction, fraud detection and rug pull prediction. Developers and platforms can integrate these tools through the MCP protocol to safeguard DeFi users, monitor liquidity risks, and score wallet or contract trustworthiness. All tools follow the Model Context Protocol (MCP) and can be consumed via MCP-compatible clients. The server exposes three main tools: predictive_fraud (Predictive Fraud Detection), predictive_behaviour (Predictive Behaviour Analysis), and predictive_rug_pull (Predictive Rug‑Pull Detection). Each tool accepts an API key for production usage, a target network, and a wallet or contract address, and returns structured JSON with fields such as status, probabilityFraud, lastChecked, forensic_details, and timestamps (createdAt/updatedAt). The outputs include human-readable messages and forensic metrics, and may utilize Server-Sent Events (SSE) for real-time responses. Access is restricted by API keys; production endpoints require authentication. The service is public tools with a private backend, hosted at https://prediction.mcp.chainaware.ai/, and designed to be consumed by MCP-compatible clients.