mcp-benchmark-hygiene is a deterministic command-line tool that detects pytest configuration leakage affecting agent-benchmark grading. It helps developers and benchmark maintainers identify issues such as unintended coverage options that can mis-score evaluations.
mcp-benchmark-hygiene is an Agent evaluation & testing project. It focuses on preventing hidden pytest configuration from distorting automated agent-benchmark scores. It is built as an open-source project for developers and AI benchmark maintainers. mcp-benchmark-hygiene is open source. mcp-benchmark-hygiene is available on the command line, and it can be self-hosted.
It is developed by sudo-ai-git. Key capabilities include pytest inspection, config leakage detection, and benchmark validation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do