evalgate for Claude Code

io.github.ipezygj/evalgate

Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).

client:Claude Code transport:stdio runtime:pypi

Install evalgate in Claude Code

run in your project directory

claude mcp add evalgate -- uvx eval-integrity

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs