Conceal

Proxy server that intercepts communications to automatically detect and replace personally identifiable information with consistent fake data using configurable regex patterns and optional LLM-based detection, maintaining semantic meaning while ensuring privacy compliance.

An MCP proxy server that performs pseudo-anonymization of personally identifiable information (PII) before data reaches external AI providers like Claude, ChatGPT, or Gemini. Built in Rust by Gianluca Brigandi, it intercepts MCP communications and uses configurable regex patterns combined with optional Ollama LLM-based detection to identify PII such as emails, phone numbers, SSNs, and IP addresses, then consistently replaces them with realistic fake data while maintaining semantic meaning and data relationships. The implementation includes a SQLite-backed mapping store for consistent anonymization across sessions, supports multiple detection modes (regex-only, LLM-only, or hybrid), and is designed for organizations that need to analyze sensitive data with AI assistants while preserving privacy and regulatory compliance.