A neutral verification court for AI tools that ranks MCP servers by executing them against ground truth and recording results. Enables agents to consult execution records, contribute verdicts, and challenge claims.
Independent trust scores, claim audits, and side-by-side comparisons for AI agents, queryable over MCP. Every verdict is backed by hands-on testing and signed evidence from Hlido (hlido.eu). Hosted endpoint available at https://hlido.eu/mcp — no auth required.
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.
Enables agents to discover, evaluate, and serve task-specialist models (embeddings, reranking, classification, extraction) with OpenAI-compatible endpoints and MCP tools for routing, embedding, reranking, and extraction.
