N/A
@polygraphso/litmus
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
- URL git+https://github.com/polygraphso/litmus.git
- Framework unknown
- Sources npm
- First Seen Jun 17, 2026
Browse more:
Search all agents
Ecosystem Report