REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Human-in-the-loop for AI agents: ask a person and get approvals or answers by push notification.
claude mcp add --transport http pushary https://pushary.com/api/mcp/mcp
This server is designed to route agent approval requests and follow-up questions to a phone so a user can respond away from the terminal. It is for people running long-lived agent workflows who need lightweight human-in-the-loop access on mobile. The idea is practical, but it is still a specialized convenience layer and should be vetted for notification reliability and security around approvals.
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.