Adverse Media Check

Search adverse news about a person or company. Returns a risk level, category counts and linked headlines for review.

Pay by wallet (x402) adverse-media-check

Example

Example answer
{
  "query": "Wirecard AG",
  "period": "last 12 months",
  "source": "dilisense",
  "categories": {
    "political": 19,
    "regulatory": 94,
    "financial_crime": 187,
    "organized_crime": 12
  },
  "risk_level": "high",
  "total_hits": 312,
  "screened_at": "2026-04-27T13:00:00.000Z",
  "top_articles": [
    {
      "category": "financial_crime",
      "headline": "Wirecard scandal: how the German fintech collapsed",
      "language": "en",
      "timestamp": "2026-04-20T10:00:00",
      "source_link": "https://example.com/wirecard-scandal"
    }
  ],
  "lists_queried": {
    "version": null,
    "collection": "dilisense/adverse-media",
    "source_count": 235000,
    "last_updated_at": null
  },
  "categories_found": [
    "financial_crime",
    "regulatory",
    "organized_crime",
    "political"
  ],
  "severe_categories": [
    "financial_crime",
    "organized_crime",
    "terrorism",
    "violent_crime"
  ],
  "risk_level_thresholds": {
    "low": "total_hits > 0 AND no hits in severe categories (financial_crime, organized_crime, terrorism, violent_crime)",
    "high": "10+ hits in any single severe category",
    "none": "total_hits == 0",
    "medium": "1+ hits in any severe category"
  }
}

Inputs

FieldTypeRequiredWhat it is
namestringYesPerson or company name to screen
countrystringNoAdditional context like industry or country (optional)
entity_namestringNoAlias for name (optional)
entity_typeone of person, companyNoOverride auto-detection of entity type (optional)

Output fields

How reliably each field appears in a successful answer.

FieldTypeAppears
querystringAlways (present in every successful answer)
periodstringAlways (present in every successful answer)
sourceone of dilisense, serperAlways (present in every successful answer)
categoriesobjectAlways (present in every successful answer)
risk_levelone of none, low, medium, highAlways (present in every successful answer)
total_hitsintegerAlways (present in every successful answer)
screened_atstringAlways (present in every successful answer)
top_articlesarrayAlways (present in every successful answer)
lists_queriedobjectAlways (present in every successful answer)
fallback_reasonstring or nullSometimes (present only for some inputs)
categories_foundarrayAlways (present in every successful answer)
severe_categoriesarrayAlways (present in every successful answer)
risk_level_thresholdsobjectAlways (present in every successful answer)
unresolved_source_links—Usually (present for most inputs)
link_resolution_attempted—Usually (present for most inputs)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "adverse-media-check",
    "inputs": {
      "name": "Wirecard AG",
      "entity_type": "company"
    },
    "max_price_cents": 20
  }'

Limitations

  • AI-classified results may miss subtle risk signals

    AI-classified results — may miss subtle risk signals or produce false positives

  • Limited to publicly indexed web content

    Limited to publicly indexed web content — paywalled news sources not covered

  • English-language bias

    English-language bias — non-English media coverage may be underrepresented

  • Recency depends on search index freshness

    Recency depends on search index freshness (typically 24-48h delay)

  • AI-categorized results may produce false positives for common names

    AI-categorized results — may produce false positives for common names or names that appear in unrelated news contexts

    What to do instead: Review top articles manually to confirm relevance. Use entity_type parameter to improve precision

  • Screens 235,000+ sources but paywalled content may not be fully indexed

    Screens 235,000+ sources but paywalled content may not be fully indexed. Non-English language coverage varies by region

    What to do instead: For high-stakes screening, supplement with manual searches in local-language news sources

  • Articles typically appear in near real-time with 24-48 hour indexing delay for some sources

    Articles typically appear in near real-time but some sources may have a 24-48 hour indexing delay

    What to do instead: For breaking news events, supplement with direct web search