hallucination_check

Active

declared in 1.0.0

Compare an agent's statement against ground truth evidence. Detects factual mismatches and dangerous hallucination patterns (absolute language, suspect claims). Returns evidence checks and red flags.

Parameters schema

{
  "type": "object",
  "required": [
    "statement"
  ],
  "properties": {
    "context": {
      "type": "string",
      "description": "Optional context for the statement"
    },
    "statement": {
      "type": "string",
      "description": "The statement to check against evidence"
    }
  },
  "additionalProperties": false
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.50.

Parent server

io.tooloracle/trustlayer

https://github.com/ToolOracle/trustlayer

1/7 registries

View full server →