An MCP server that audits LLM-as-judge evaluations, detecting judge drift across runs, measuring bias through controlled probes, and comparing judge agreement with human raters.
An MCP server that enforces a scientific-method loop for AI-driven machine learning experiments, with hypothesis gating, diagnostics, and data forensics.
MCP server for mechanistic interpretability research, enabling agents to drive probe-causality and SAE-feature experiments via 8 typed tools on user's own compute (Colab).
MCP server for verifying AI agent claims vs reality — single-transcript inline grounding-check that flags when an agent's response states facts not in the input context, when its code silently swallows exceptions and substitutes mock data, or when its multi-turn transcript contains contradictions or unverified completion claims. Sub-second, local, free, no API calls.
An MCP server that provides tools to audit AI-agent marketplace integrity by scanning listings for deceptive patterns like fabricated engagement, automated seeding, self-advertisement, unpaid work risk, and high-budget bait.