REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Pseudonymizes PII before your LLM and returns a cryptographically signed receipt per response.
claude mcp add lucairn-mcp-server -- npx -y @lucairn/[email protected]
An EU privacy gateway for LLM calls: the chat_via_lucairn tool routes prompts through gateway.lucairn.eu, which strips PII (Presidio NER plus entity matching) before the text reaches Anthropic or OpenAI, and returns a cryptographically signed redaction certificate. The monorepo is substantive — TS, Python, and Go SDKs with tests — and the docs are unusually candid. Two things to weigh: every prompt (and on the free BYOK tier, your upstream Anthropic/OpenAI key, forwarded per-request) transits their gateway, and the free tier returns placeholder tokens like [PERSON_1] verbatim rather than re-linked text, which limits it to testing the redaction surface.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.