REA
Verified · 35 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails.
claude mcp add mcp-server -- npx -y @declaw/[email protected]
Provides Firecracker-based sandboxing controls for AI agents, with an emphasis on network restrictions and safety guardrails around PII and prompt injection. It is aimed at teams experimenting with higher-isolation agent execution rather than general MCP users. The concept is relevant, but the package looks very early with minimal visible adoption, so it reads as promising infrastructure work rather than a mature default choice.
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.