REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcp
This server focuses on detecting prompt injection and exfiltration attempts for AI agents, with an explicit security posture around MCP-related threats. It is for teams running agents in higher-risk environments who want a dedicated guardrail rather than a general-purpose tool server. The security focus is relevant, but the strong formal-verification claim is not something to assume from the listing alone, so it should be treated as promising but still verify-before-relying.
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.