A zero-cost, fully local MCP server that grounds AI assistants in verified web text, reducing hallucinations by ~80% by forcing answers only from fetched sources.
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 that lets coding agents test AI agents. Create YAML test cases, snapshot golden baselines, check for regressions, and generate visual reports all from inside Claude Code or any MCP-compatible tool. Works with LangGraph, CrewAI, OpenAI, Claude, Mistral, and any HTTP API.
MCP server for AI compliance auditing. Scores agent outputs for hallucination liability under the EU AI Act, issues verifiable compliance stamps, and tracks audit history by agent.