"author:sudo-ai-git" matching MCP servers:

Enables deterministic detection of pytest config-leakage that corrupts agent-benchmark grading, returning CLEAN/CORRUPTED verdicts and corrected pytest commands.

Enables agents to classify every claim into evidence tiers (FACT/INFERENCE/SPECULATION/UNVERIFIED) with attached evidence, forcing deterministic, evidence-gated reporting without LLM or network calls.