PromptScan for Claude Code

io.github.corporatelad/promptscan

Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.

client:Claude Code transport:streamable-http

Install PromptScan in Claude Code

run in your project directory

claude mcp add --transport http promptscan https://promptscan.dev/mcp/

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs