Rayana AI MCP Server

The portfolio-analyst brief with its per-ticker views — the broadcast opinion layer, identical for every caller.

The public articles feed, newest first, when ``slug`` is omitted; one published article's full body when ``slug`` is given.

Exchange a pairing code from your principal's account page for an API key. Ask them to confirm before you call this: it issues a new key and immediately invalidates the account's previous one, so any other client already using a key will stop working until it is given the new value. The key comes back once and is not retrievable afterwards — only a hash of it is stored. Put it in the ``X-API-Key`` header on this connection and on any REST call. Codes are single-use, expire in 15 minutes, and are burnt after a few wrong guesses; if one is refused, ask for a fresh one rather than retrying.

Per-source consensus snapshots (insider trades, congressional trades, earnings beats, dated catalysts, on-chain flows, 13F filings, AI news-beneficiary reads). Omit ``source`` for every source at once, or pass one of the slugs returned in a rankings/signals row's source list. ``limit`` caps rows per source. The sources are very unevenly sized — institutional holdings runs to ~1700 rows where on-chain flows may have two — so a source that comes back with exactly ``limit`` rows probably has more, and narrowing with ``source`` and raising ``limit`` reads that one layer deeply for far less context than raising ``limit`` across all seven.

Which lanes (daily/turtle/mr) currently have a batch available.

The daily market brief: a generic engine-wide read with no recommendations, descriptive only. Latest by default; pass ``date`` (YYYY-MM-DD) for a specific day.

What Rayana AI costs and what each tier unlocks. No API key needed — call this first if a research tool refused you for want of one. API and MCP access start at the Pro tier. Prices are USD; annual billing is ten months' price for twelve. Use ``rayana_ai_start_checkout`` to turn a choice here into a link your principal can open.

One model portfolio's full detail: holdings, overlay legs, event feed, NAV series, and windowed returns. Returns an error if the slug's tier (e.g. an Elite-only book) is above this key's own tier — a Pro key does not get Elite content just because it has MCP access.

The full shelf of Rayana AI's broadcast model portfolios as merchandising cards, with each card's tier/openable/delayed flags.

Latest ranked candidate batch for a lane: daily (the main research lane), turtle (breakout system), or mr (mean-reversion). Rows come back in rank order, best first, so the default page is the top of the batch. ``total`` in the response is the batch size; when it exceeds ``count``, page with ``offset``. ``include_assessment`` adds each row's technical blob (pattern and cluster validation, volume profile) — it triples the response, so prefer ``rayana_ai_ticker`` for one name's detail and leave this off when scanning.

Cluster-rotation layer. ``summary``: latest per-cluster RRG quadrant/rank rows with deltas, plus the most recent quadrant-crossing events (``days`` controls the window both are computed over). ``laggards``: members trailing a firing cluster's leader. ``discovered``: unsupervised cluster-discovery cohorts the structural taxonomy misses. ``members``: structural cluster membership. On ``summary``, two blocks are trimmed because together they are 80% of the response while answering a narrower question than the rows do. ``include_trajectory`` adds each cluster's full rank series — a chart payload, off by default. ``events`` returns the newest 25 crossings; if exactly 25 come back there are probably older ones, and a wider ``days`` is not what returns them.

Resolve free text (ticker or company name) to known Rayana AI symbols, best match first. Pure resolution — never accrues signal.

Latest aggregator-consensus batch for one asset lane: which tickers cleared the signal pipeline, blended agg_score, confirming source count.

Get a link your principal opens in a browser to subscribe. No API key needed. Give them the URL — you cannot complete this yourself, and should not try: they sign in, accept the Terms and authenticate the payment. Afterwards they will see a short pairing code on their account page. Read it back into ``rayana_ai_complete_setup`` to get your API key without them pasting a secret into this conversation.

Full per-ticker research view: score, lane membership, per-source signals, virality, consensus, cluster-rotation position, forward returns.

Today's cached AI ticker-analyst read (lean, conviction, thesis, evidence for/against, invalidation condition). Never triggers a new model call; 404s if nothing was generated today for this ticker.

One ticker's published article history, newest first.

Daily close-price history for one ticker over the given period. Long periods are evenly sampled down to ``max_points`` bars rather than cut short, so the series still spans the whole period — ``5Y`` and ``MAX`` return the shape of the history, not its last year. ``last_close``, ``change_pct`` and the ``range_low``/``range_high`` extremes are computed over every bar regardless of sampling.

The attention leaderboard: latest virality snapshot ranked by VScore, with the full intensity/breadth/slope/vramp decomposition.

The attention layer's raw texture. ``sources``: per-source reach today. ``heat``: per-(ticker, source) attention contributions. ``search``: rising/breakout consumer search queries. ``video``: rising video-view velocity. ``limit`` applies to search/video only; omit it to use that view's own default.