Nota

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Read-only crypto research skills that check a price, RSI and ATR against independent sources.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Nota": {
      "url": "https://nota-ryo.vercel.app/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (9)

• narrative_convergence read-only

  Monitor up to 20 user-selected voices (Telegram public channels, Bluesky and X handles) and report which tokens they mention, lexicon-scored sentiment per token, conviction and urgency, and whether the voices converge: at least two voices carry a non-zero net sentiment on the token and every one of them has the same sign.

  Parameters:

  • voices (required) — array — Up to 20 ids like tg:WatcherGuru, bs:handle.bsky.social or x:handle
  • hours — integer — Look-back window in hours (default 24)
  • tokens — array — Symbols to track; default = every cashtag, ticker or name of a known major found

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• news_verify read-only

  Verify a crypto news claim: count independent domains reporting it (four outlets' RSS headlines plus Tavily or Venice web search), count those whose headline leans the opposite way, and attach the token's RYO analyze_token evidence so the story and the market read sit side by side.

  Parameters:

  • claim (required) — string — The story to verify, in one sentence
  • symbol — string — Token symbol to attach market evidence for
  • max_results — integer — Search results to inspect (default 6, max 20)

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• price_crosscheck read-only

  Fetch independent USD spot prices for a symbol from CoinGecko, Coinbase, Kraken, Binance and DefiLlama (no keys), drop a source that disagrees with the rest as an outlier, report median and spread, and flag how far a reference price (e.g. RYO's) deviates from them.

  Parameters:

  • symbol (required) — string — Token symbol, e.g. SOL
  • reference_path — string — Where the reference price came from
  • reference_price — number — Price to compare against, e.g. RYO deep_analysis price
  • reference_fear_greed — number — A Fear & Greed value to compare with alternative.me

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• technicals_crosscheck read-only

  Recompute RSI(14) and ATR(14) (Wilder smoothing) from 200 closed UTC-day candles (OKX, else Binance, else CoinGecko 4h OHLC aggregated to days) plus 1d/7d/30d performance, and report how far reference values (e.g. RYO's) deviate from the independent calculation.

  Parameters:

  • symbol (required) — string — Token symbol, e.g. SOL
  • days — integer — lookback for performance, 7..90 (indicators always use 200 closed daily candles)
  • reference_atr_14 — number — ATR(14) in USD to compare against
  • reference_rsi_14 — number — RSI(14) to compare against

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• positioning_check read-only

  Decide, field by field, whether RYO's deep_analysis derivatives block can be cited as evidence about this token (identical values across other tokens, sign conflicts with OKX coin-terms open interest), and report OKX perp positioning: premium over spot on OKX and Hyperliquid, 24 h open-interest change in coins, long/short account ratio and its 100-hour percentile, and for BTC/ETH Deribit's DVOL implied 7-day move as a check on stop distance.

  Parameters:

  • symbol (required) — string — Token symbol, e.g. SOL
  • atr_stop_pct — number — Stop distance in % of price (e.g. RYO's 1.5 x atr_14_pct), checked against the DVOL implied 7-day move
  • peer_derivatives — array — Same-day RYO derivatives blocks for other symbols: [{symbol, funding_rate_bps, open_interest_change_24h_pct}]; taken from the day's scorecard locks when omitted
  • ryo_btc_funding_bps — number — Latest BTC funding from RYO monitor_market_sentiment_shift (evidence.funding.latest_bps)
  • reference_derivatives — object — RYO deep_analysis data.derivatives for this symbol; fetched from RYO when omitted and a RYO key is set

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• move_base_rate read-only

  Empirical probability that a token moves k ATRs (up or down, touched or closed beyond) within h days, counted from ~400 days of OKX daily candles on days in the same ATR tercile as today, with a time-split holdout. Pass RYO's atr_14_pct to measure the distance in RYO's ATR; k=0 with event=close gives the plain 'higher after h days' rate.

  Parameters:

  • symbol (required) — string — Token symbol, e.g. SOL
  • k — number — Distance in ATRs (default 1)
  • as_of — string — YYYY-MM-DD: use only candles closed before this day (scoring a past call)
  • event — string — Default touch
  • direction — string — Default up
  • atr_14_pct — number — RYO's ATR(14) as % of price (analyze_token or deep_analysis)
  • horizon_days — integer — 1 to 14 (default 3)

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• verdict_track_record read-only

  How RYO's own deep_analysis plans have fared: locked daily for 25 majors and settled on OKX hourly candles (stop or +1R target first, 24 h or 72 h). Returns counts by verdict and by confluence state, plans whose verdict leans against their own direction, and the latest locked verdict. Omit the symbol for all tokens.

  Parameters:

  • symbol — string — Token symbol, e.g. SOL; omit for every token
  • horizon_hours — integer — 24 (default) or 72

  Hints: read-only yes · destructive no · idempotent no · open-world no

• liquidity_check read-only

  Macro liquidity from DefiLlama (no key): 7-day and 30-day change of the total USD stablecoin supply, and of DeFi TVL on the token's own chain (ETH, SOL, BNB, AVAX and other L1/L2 tokens). Each leg reports its own as_of and availability; a token without a chain of its own gets no TVL rather than a borrowed one.

  Parameters:

  • symbol (required) — string — Token symbol, e.g. SOL

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• crowd_odds read-only

  Prediction-market implied probability that a token trades higher than now at a horizon: the Polymarket 'above $K on <date>' ladder (Kalshi's KX<coin>D ladder as fallback) expiring within a day of now + horizon, liquid strikes only, made monotone and interpolated at spot. BTC, ETH, SOL, XRP (and DOGE on Kalshi); null when no market.

  Parameters:

  • symbol (required) — string — Token symbol, e.g. BTC
  • spot — number — Price to read the ladder at (default: Binance spot, which is what Polymarket's crypto ladders resolve on)
  • horizon_days — integer — 1 to 14 (default 7)

  Hints: read-only yes · destructive no · idempotent no · open-world yes

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.