N/A

@polygraphso/litmus

unknown agent Offline

Behavioral litmus harness for MCP servers — grade a server A–F (tool-output injection, egress, sensitive-data, adversarial-input) with reproducible, content-addressed evidence. Ships a CLI and an MCP server with a run_litmus tool for AI agents.

Scan Scheduled

This agent is queued for security scanning. It will be graded in the next scan batch.

What We Know