mcp-benchmark-hygiene is an open-source MCP server for detecting pytest configuration leakage that can affect agent-benchmark grading. It uses deterministic, no-LLM checks and is intended for developers maintaining reliable benchmark evaluation workflows.
In the Agent evaluation & testing space, mcp-benchmark-hygiene takes a focused approach. It focuses on preventing pytest configuration leakage from corrupting agent-benchmark grading. It is built as an open-source project for developers building and evaluating agent benchmarks. mcp-benchmark-hygiene is open source under the MIT license. mcp-benchmark-hygiene is available on the command line and API, and it can be self-hosted.
sudo-ai-git builds and maintains mcp-benchmark-hygiene, and it first shipped in 2026. Development happens publicly on GitHub with 9 commits in the last 90 days. Key capabilities include pytest config detection, leakage detection, and benchmark grading checks. It exposes integrations via an MCP server.
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