ai_act_training_data_audit

Active

declared in 0.2.0

As a CTO, audit AI training datasets for EU AI Act compliance with bias detection and regulatory risk assessment. Inputs: dataset identifier (Hugging Face ID or URL) and optional risk thresholds. Outputs: compliance score, bias metrics, regulatory warnings, and source references. Ideal for pre-deployment risk evaluation. Pass async:true to avoid timeout.

Parameters schema

{
  "type": "object",
  "required": [
    "dataset_id"
  ],
  "properties": {
    "async": {
      "type": "boolean",
      "description": "If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts."
    },
    "dataset_id": {
      "type": "string",
      "description": "Hugging Face dataset identifier or direct URL to dataset"
    },
    "risk_threshold": {
      "type": "number",
      "default": 0.7,
      "maximum": 1,
      "minimum": 0
    },
    "include_bias_metrics": {
      "type": "boolean",
      "default": true
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

gapup-mcp

https://github.com/getgapup/gapup-mcp-public

2/7 registries

View full server →