MCP server exposing statistical regression testing for LLM agents as a "run" tool: p-value, effect size, and confidence interval on whether agent behavior actually changed.
An MCP server that lets any AI agent evaluate RAG outputs -- faithfulness scoring, hallucination detection, and retrieval quality metrics -- with zero API keys, using MCP sampling.
MCP server for a modular RAG system that enables natural language question answering over enterprise documents with intent-aware routing, adaptive retrieval, and citation-backed responses.
MCP server that analyzes AI agent execution logs to calculate reliability scores, detect failure patterns, and suggest concrete improvements for making AI agents more reliable.
RegressGuard is an MCP server that records a known-good baseline and lets AI coding agents detect regressions (broken API contracts, failing tests, schema changes) during their edit loop, allowing them to self-correct before committing.