REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
claude mcp add mcp-server -- npx -y @emilia-protocol/[email protected]
A control-layer server designed to require human approval before agents take irreversible actions. It is for teams concerned with governance, auditability, and reducing autonomous agent risk in sensitive workflows. The concept is useful and increasingly relevant, though the current adoption signals suggest an early implementation rather than a widely established standard.
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.