Trending keywords

Every field the corpus returns for one record. Real shape — walked corpus-wide, not sampled.

{
  "id": 40834,
  "keyword": {
    "id": 211,
    "name": "Bitcoin",
    "tag": { "id": 136, "slug": "bitcoin", "name": "bitcoin" },
    "match_type": "phrase",
    "case_sensitive": false,
    "required_terms": []
  },
  "sentiment_score": "0.00",
  "trending_order": 0,
  "trendiness": "0.63"
}

A curl that runs against the live API right now, plus the MCP tool names for the same data.

curl https://api.alphaday.com/keywords/trending/

MCP tools

Three concrete questions this capability answers that a general crypto API does not.

• Letting the data pick the subject: an agent that starts here finds stories nobody put on a watchlist, which is the loop /cookbook/crypto-research-agent runs.
• Composability, which is the real reason to use this: each entry carries keyword.tag.slug, and that slug is accepted by every other feed — so a trending term turns straight into news, governance and price queries.
• Mood alongside momentum: trendiness says how much attention a term is getting, sentiment_score says how the coverage reads. A term trending hard at negative sentiment is a different story from one trending hard at positive.