Conceal
Proxy server that intercepts communications to automatically detect and replace personally identifiable information with consisten
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.
Source
Repository: https://github.com/gbrigandi/mcp-server-conceal
Maintain Conceal?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Conceal on getagentictools](https://getagentictools.com/mcp/gbrigandi-mcp-server-conceal?ref=badge) Related mcp
Cross-Claude Message bus enabling communication between AI instances across platforms through shared channels, threaded conversations, and data
Fitness Coach Provides personalized fitness coaching through workout and nutrition plan generation, activity logging, progress tracking, and fee
MongoDB Enables interaction with MongoDB databases through TypeScript and the MongoDB driver, providing seamless integration of MongoDB op
PolarDB Provides a bridge between natural language interfaces and Alibaba Cloud PolarDB databases, enabling direct interaction with MySQL
N3MO Code intelligence engine mapping repositories into queryable symbol graphs.
PostGIS Provides direct PostgreSQL database integration with PostGIS spatial extension support, enabling SQL query execution, spatial data