REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.
claude mcp add umbryn-mcp -- uvx umbryn-mcp
A privacy-focused server that redacts PII and PHI before prompts reach an LLM, with a self-hosted, fail-closed, no-egress design. It is for teams in regulated or privacy-sensitive settings that need a guardrail layer in front of model calls. The security posture described is sensible and narrowly focused, but the project still looks early from the available signals, so effectiveness and coverage should be tested rather than assumed.
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.