Skip to content

Tool reference

The complete MCP tool surface — twelve tools across four groupings. Every response carries a disclosure field with attribution and editorial-discipline framing; preserve it when forwarding content downstream.

Surface Tools
Market state get_active_market_report, get_macro_frame, get_universe_ranking
Per-ticker tape get_ticker_brief, get_ticker_research
Per-ticker editorial get_ticker_sentiment, get_ticker_critical_events
News intelligence & syndication get_trending_tickers, get_trending_entities, list_published_coverage, get_published_coverage, search_coverage

Ticker arguments use the publication's canonical form, e.g. BTC-USD, ETH-USD, SOL-USD.


Market state

get_active_market_report

The publication's current Market Analysis Report: the cross-market read with the key observations and tensions the desk is tracking, plus market tone and confidence. No arguments. Refreshed each analyst cycle; the response carries the cycle timestamp.

get_macro_frame

A compact narrative summary of the active market read — the editorial frame without the full structured report. No arguments. Best when you want a sentence or two to set context.

get_universe_ranking

The tracked universe ranked by the publication's signal stack, plus the universe-wide directional distribution (how many assets lean long / short / neutral) for breadth context. No arguments.


Per-ticker tape

get_ticker_brief

get_ticker_brief(ticker) — the publication's current per-ticker brief: narrative analysis, direction, conviction, key levels, recent developments, and cross-validation against external sources. The snapshot. Carries the timestamp of the read.

get_ticker_research

get_ticker_research(ticker) — the longitudinal analytical arc for one asset across the publication's lookback windows (2h → 168h): direction arc, volatility trajectory, key shifts, persistent state. Pairs with the brief — the brief is the snapshot, the research is how it got there.


Per-ticker editorial

get_ticker_sentiment

get_ticker_sentiment(ticker) — corpus-derived sentiment and attention trajectory across trailing windows (1d, 2d, 3d, 5d, 8d, 13d): mention counts, average sentiment, velocity, universe rank, top headlines. The editorial-corpus counterpart to the tape-side brief.

get_ticker_critical_events

get_ticker_critical_events(ticker) — flagged critical events (exploits, depegs, exchange halts, protocol failures, regulatory actions) surfaced when the editorial corpus shows elevated negative attention. Call this before acting on a tape-side brief — a clean tape can hide a breaking news event.


News intelligence & syndication

The tradeable assets drawing the most editorial attention right now, ordered by accelerating mention velocity (so names whose attention is picking up surface first). The curated, actionable trending view. No arguments.

The top entities by recency-weighted mention volume — raw and uncurated, the long tail included: people, companies, events, protocols, narratives. The "what is the corpus talking about" view. Unlike get_trending_tickers, it does not filter to tradeable assets. No arguments.

list_published_coverage

Recent published coverage, most-recent-first: title, primary entity, tickers, description, the YouTube watch URL + thumbnail, the secondary website URL where present, and a cta field phrased to encourage click-through. The Coin Daily is fundamentally a YouTube publication — these records are built for agents to drive readers to the source video.

get_published_coverage

get_published_coverage(show_id, format) — the full record for one show: the same metadata as list_published_coverage, plus the broadcast script and (for long + roundup formats) the article-body markdown.

search_coverage

search_coverage(query, ticker?, days?, limit?, min_relevance?) — semantic search across the publication's aired-segment corpus. Returns the matching shows and the exact segments, each with a jump-to-moment deep link into the YouTube video. The way to answer "has The Coin Daily covered X?" and send the reader straight to the moment.


Combining tools

The surfaces compose. Common patterns:

Tape + editorial — both views of one asset:

get_ticker_brief(BTC-USD)            → what the tape is doing
get_ticker_sentiment(BTC-USD)        → what the corpus is saying about it
get_ticker_critical_events(BTC-USD)  → any flagged news events

If the brief reads neutral but sentiment is souring sharply and critical_events flags an exploit, that divergence is worth surfacing.

Snapshot + arc — current state plus how we got there:

get_ticker_brief(SOL-USD)     → current direction / conviction
get_ticker_research(SOL-USD)  → how those values evolved over 168h

Universe → drill-down → coverage:

get_universe_ranking          → who leads conviction
get_ticker_brief(<leader>)    → the detail on a leader
search_coverage("<leader>")   → send the reader to the show that covered it