prompt-protection MCP
v4.0.0io.github.mughalhere/prompt-protection
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
transport:stdio
runtime:npm
Target client
run in your project directory
claude mcp add prompt-protection -- npx -y prompt-protection
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.