rigor-mcp is an MIT-licensed Python package that provides verified statistical inference for AI agents. It offers classical hypothesis tests, effect-size calculations, power and sample-size analysis, multiple-comparisons correction, and access through both a CLI and MCP server.
rigor-mcp is a Frameworks & runtimes project. It focuses on helping AI agents perform statistically valid hypothesis testing and power analysis instead of relying on unverified calculations. It is built as an open-source project for AI agent developers and data scientists. The project is open source (MIT). It ships for the command line, and it can be self-hosted.
mrnh builds and maintains rigor-mcp, and it first shipped in 2026. Development happens publicly on GitHub with 6 commits in the last 90 days. Key capabilities include hypothesis testing, effect sizes, and power analysis. 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