Sensitive Data Exposure Detector MCP Connector for Claude

This MCP server acts as a security layer that intercepts, analyzes, and redacts sensitive information from file reads and tool outputs before they enter the LLM context. It uses deterministic regex patterns to detect AWS keys, GitHub tokens, private keys, database connection strings, and JWTs. It also identifies high-entropy strings using Shannon entropy calculation. By using scan_content, users can clean raw text, while get_redaction_audit provides a traceable history of all redactions. The validate_safety_threshold tool allows for automated security enforcement based on exposure risk scores.