REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
claude mcp add agentguard47 -- npx -y @agentguard47/[email protected]
This server exposes read-only telemetry around coding-agent activity, including traces, alerts, costs, usage, and budget status. It is best suited to teams running agents in production or testing who need lightweight oversight without write access. The scope is clear and practical, but current traction looks modest, so maturity should be treated as emerging rather than established.
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.