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 LLM agents to route responses as accept, verify, or ask-a-human based on token logprobs, and provides an MCP server for delegating generation to local models with confidence bands.
Semantix-Verify is an MCP server for semantic validation of AI/LLM outputs. It exposes a single tool, verify_text_intent(text, intent_description, threshold), which uses
a local quantized NLI cross-encoder (INT8 ONNX) to return a 0.0–1.0 probability that the text satisfies the given intent — and, when it doesn't, a structured correction
prompt for agent retry loops. Useful for building com
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.
A benchmarked hallucination detector that returns unsupported claims with details. Runs as an MCP server with two modes: sampling (default, no API key) and direct API.