hallucination_
1 MCP server offers this tool
What it usually takes
answer– in 1 of 1knowledge– in 1 of 1mc_passes– in 1 of 1question– in 1 of 1task– in 1 of 1threshold– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Hallucination Detector (DeBERTa) co.huggingface.hugging-apps/hallucination-detector-deberta Classify an LLM answer as Factual or Hallucinated given a knowledge context. Runs the fine-tuned DeBERTa-v3 detector once for the headline score, then runs Monte-Carlo Dropout passes for an uncertainty estimate (std dev across stochastic forward passes), exactly as in the paper. Returns: (verdict label dict, details markdown). | answer,knowledge,mc_passes,question,task,threshold | Not stated |