REA
Verified · 8 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Give agents an ask_human tool: escalate decisions to real people and get judgments back.
claude mcp add askhuman -- npx -y @thrain/[email protected]
This server adds an ask_human capability so an agent can hand decisions or judgment calls to a real person. It is for teams building workflows that need explicit human escalation, approvals, or ambiguity resolution. The idea is broadly useful, but the package shows little adoption signal from the metadata provided, so it looks early-stage rather than established.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
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.
Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.