PromptGuard MCP
v1.1.2co.promptguard/security
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
transport:stdio
runtime:npm
Target client
run in your project directory
claude mcp add security -e PROMPTGUARD_API_KEY=<PROMPTGUARD_API_KEY> -- npx -y @promptguard/mcp-server
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.