Enables agents to encrypt and sanitize sensitive data such as credentials, credit card numbers, and addresses locally before dispatching prompts to cloud LLMs, then rehydrate the masked values client-side. It runs deterministically with zero external dependencies over MCP JSON-RPC stdio, so no plaintext PII leaves the user's machine.
Provides MCP tools for prompt injection detection and content sanitization, safeguarding LLM pipelines. Also enables Japanese PII scanning and masking for secure data handling.
Local pseudonymisation MCP server that detects PII in text, replaces it with opaque tokens before sending to cloud LLMs, and restores tokens afterward.
Enables MCP clients to safely connect to MCP servers by sanitizing sensitive data in tool results and restoring it in tool arguments, so the model never sees PII while downstream tools still receive real values.