promptrejectormcp MCP
v1.0.1io.github.revsmoke/promptrejectormcp
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
transport:stdio
runtime:npm
Target client
run in your project directory
claude mcp add promptrejectormcp -e YOUR_API_KEY=<YOUR_API_KEY> -- npx -y prompt-rejector
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.