Sits between Claude and your upstream LLM provider (Anthropic, OpenAI) and strips PII before prompts reach the model. Runs via `npx @lucairn/mcp-server` with zero install. Exposes a `chat_via_lucairn` tool that runs a three-layer detection pipeline (known entities, Presidio NER for emails/IBANs/phone numbers, optional GPU-trained shield on Enterprise). Returns cryptographically signed receipts (Ed25519 + RFC 3161 timestamp + Sigstore Rekor proof) showing what was redacted and when. Free tier returns placeholders verbatim for testing redaction coverage. Pro and Enterprise re-link originals on the gateway after the model responds. Reach for this when you need audit-grade proof that personal data never touched the model, especially in regulated contexts where you want BYOK provider billing plus compliance certificates your DPO can verify.
claude mcp add --transport stdio io.github.declade-lucairn-mcp-server uvx lucairn-mcp-server