REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.
claude mcp add phantom-secrets-mcp -- npx -y [email protected]
This is a security-focused MCP utility that proxies secrets so coding agents see placeholder tokens instead of raw API keys. It is for developers running local agent workflows who want an extra safeguard against accidental secret exposure in prompts, logs, or tool output. The idea is useful and concrete, but it is also a narrow control layer rather than a complete secrets solution, so it should be evaluated as defense-in-depth rather than a primary security boundary.
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.