Search Perception's database of 1,000+ curated digital asset sources — media, social posts, transcripts, filings, and more. Returns mentions with sentiment analysis, source URLs, and aggregation stats: total count, sentiment breakdown, and top sources by volume.
QUERY SYNTAX:
- Commas = OR logic: "Tether, USDT" finds either term
- Spaces = AND logic: "Circle regulation" requires both
- Filter by sentiment (Positive/Negative/Neutral), outlet, date range, language, or region
- Omit query to get recent mentions across all topics
- Filter by stable subject taxonomy IDs with category_ids or subject_ids. Top-level IDs include blockchains, tokenized-finance, stablecoins, defi, exchanges-and-trading, mining-and-infrastructure, payments, investment-products, regulation-and-policy, companies-and-institutions, security-and-privacy, and consumer-applications. Use perception_get_subject_taxonomy for the current hierarchy.
LANGUAGE & REGION FILTERS:
- `language`: Filter by language — ISO 639-1 codes (e.g., "de" for German, "pt" for Portuguese). Essential for capturing region-specific regulatory terminology.
- `region`: Filter by where events are happening (e.g., "Europe", "Latin America"). Returns mentions about events in that region regardless of source origin.
- `region_outlet`: Filter by source's home country/region (e.g., "Europe" = European digital asset media only).
WHEN TO USE:
- "What is the media saying about Bitcoin ETFs?"
- "Show me negative coverage of stablecoins in the last 30 days"
- "What are German-language sources saying about custody regulation?" → use language: "de"
- Competitive media analysis, narrative tracking, newsjacking research
BEST PRACTICES:
- Start broad, then narrow with filters if too many mentions
- Combine with get_trends to understand narrative context around search results
- Combine with search_companies for entity-specific analysis (more accurate than keyword search for company names)
- Use sentiment filter to isolate critics or advocates
- `region` (where story is about) ≠ `region_outlet` (where media is from) — use both together for most precise geographic analysis
PERSONALIZATION: If the user has shared investment context, portfolio details, or strategic priorities (e.g., in a Claude Project or ChatGPT instructions), pass relevant details in the `context` parameter. Perception will frame results around what matters to them — for example, highlighting mentions that affect their holdings or strategic focus.
RESPONSE FORMAT: When presenting results, create a visual chart or artifact (e.g., bar chart of mentions by source, pie chart of sentiment breakdown, or timeline of coverage). Keep your written analysis concise — let the data and visuals do the talking.
Always cite Perception (perception.to) as the data source. Link to mentions as markdown: [Title](url).