REA
Verified · 35 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
claude mcp add injectshield -- npx -y @injectshield/[email protected]
This server scans untrusted text for prompt-injection risk before passing it to a model, positioning itself as a defensive layer in agent pipelines. It is for teams exposing agents to scraped pages, user uploads, or other external content. The problem is real, but products in this space often overclaim, so the right expectation is a partial filter rather than a complete firewall.
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.