We just released a new version of Patronus Protect:

• Improved onboarding + enforce /Applications folder

• Improved stability for gRPC connections

• Improved handling of unknown carrier protocols like protobuf, msgpack, binary

  • AI Detection in Cursor, Windsurf, Warp, ... IDEs work now

• Some more extraction patterns

• Added heuristical threat analysis.

  • See why req, res, tools, mcps where flagged

  • Currently non-blocking, pure informational

• Added ability to create Policy rules for MCP and Native Tool calls

  • Block / Allow specific tool calls before they are executed
    

Feel free to post some feedback, else see you next week with another amazing release and improvements :)

Hey PH

We are building in the AI security space right now, and there's one question I can't get a clean answer to: when you put guardrails around LLMs, where should they actually live?