Nota MCP server
online · 100% uptimeRead-only crypto research skills that check a price, RSI and ATR against independent sources.
0 stars
Reviews
Write oneNobody has reviewed Nota yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Nota tools (9)
write = sends, deletes, buys or postscrowd_oddsFreePrediction-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.
liquidity_checkFreeMacro 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.
move_base_rateFreeEmpirical 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.
narrative_convergenceFreeMonitor 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.
news_verifyFreeVerify 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.
positioning_checkFreeDecide, 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.
price_crosscheckFreeFetch 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.
technicals_crosscheckFreeRecompute 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.
verdict_track_recordFreeHow 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.
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1041ms20/20
- Tool poisoning9 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Nota compares
Against every graded Finance MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 93% of 1,761 Finance servers
- Tools
- 9
- the typical Finance server has 8
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote Finance server answers 100%
- Response time
- 339 ms
- faster than 44% of 1,133 Finance servers
What its tools let an agent do: 7 read · 1 create · 1 change
Install Nota in Claude Code, Cursor or VS Code
claude mcp add --transport http nota https://nota-ryo.vercel.app/mcp
What the publisher says
From the Nota repository's README, as published. We do not edit it. Read it on GitHub
Nota
An AI trading opinion you can audit. A council of specialised agents debates live RYO market evidence and records the practice trade it would make as a replayable decision receipt: nota replay rebuilds it from the stored evidence and prints identical: true, every cited number is read back out of the evidence rather than retyped by the model, and independent sources audit RYO's own price and indicators before anything is sized. Built for the RYO-CHAN Hackathon 2026.
Tracks entered: 1 Autonomous Agents (council, receipts, watch loop, a derivatives gate the council cannot argue past), 2 Dashboards (diff-first receipt dashboard, and the RYO Verdict Scorecard), 3 New Skills (narrativeconvergence, newsverify, pricecrosscheck, technicalscrosscheck, positioningcheck, movebaserate, verdicttrackrecord, liquiditycheck, crowd_odds, all in RYO's envelope).
RYO Verdict Scorecard
Every deepanalysis answer carries a verdict and a trade plan (a stop 1.5 ATR away, a target at +1R). RYO never reports what became of either. nota lock stores the whole answer for 25 majors once a day (never twice within 20 h); nota settle later asks OKX's public candles which level was touched first within 24 h and 72 h: 1-minute candles from the lock to the first full hour, hourly after, and an hour that touched both levels is split on its own 1-minute candles. RYO does not grade itself: the bracket is re-anchored to OKX's price at the lock, and a lock where the two prices are more than 2% apart is kept as basismismatch and never settled. A window with an hour OKX never published is retried for a day, then kept as unsettleable. Verdict pairs, confluence states and RYO's momentum gate are each compared on the target-first rate and on the return at the horizon (plans that touched neither level included): within each lock day, combined with Mantel-Haenszel weights so a lopsided day cannot flip the sign, with a p-value that shuffles labels within clusters of overlapping windows. Nothing is called distinguishable before 10 shared days and p < 0.10; a simulated null in the tests checks that rate. Every failed lock is a counted row, one per token and day however often retried, and a dead key stops the run after one call with an aborted row. The page also reports how often each lane of RYO's answer came back available, per RYO's own words. /scorecard shows it, most urgent first; /api/scorecard?horizon=24|72 is the raw record and /api/scorecard.csv the same table as CSV (one row per lock and horizon, failures included). The page carries a schema.org Dataset description (JSON-LD) naming both downloads.
Anchored in Bitcoin, not in Nota's clock. "Locked before the move" is only worth something if nobody, Nota included, can backdate a lock. nota stamp submits the SHA-256 of every good lock row and every receipt, exactly as stored, to three public OpenTimestamps calendars and keeps the .ots proof; a later run swaps in the Bitcoin attestation once the calendar has one, after checking that block's merkle root against mempool.space. The scorecard and the dashboard say "Bitcoin block N" or "timestamp pending (submitted …)" from that stored status and nothing else. To check one yourself:
curl -o lock.json https://nota-ryo.vercel.app/api/scorecard/locks/<id>.json # the row as stored
curl -o lock.json.ots https://nota-ryo.vercel.app/api/scorecard/locks/<id>.ots
ots verify lock.json.ots # pip install opentimestamps-client; or drop both files on opentimestamps.orgReceipts work the same way with /r/.json and /r/.ots.
Day 0 (2026-09-18): 25 of 25 locked, 4 CONFIRMED and 21 MIXED, and 7 plans long while RYO's own verdict was cautious (XRP, DOGE, ADA, LINK, SUI, BCH, WIF).
What the council may not cite
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-09-19restoreB → Ascore 91
Nota: common questions
- Is Nota MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Nota safety report
- How do I install Nota?
- It runs remotely at nota-ryo.vercel.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Nota need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Nota maintained?
- The last commit was 20 days ago (2026-10-14). The latest release is v0.1.0.
- Is Nota up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Nota?
- Servers from other publishers that do the same job: Shumi MCP server, Blockrun MCP server and Yolfi Payments MCP server.
- How does Nota compare with other Finance MCP servers?
- safety score 91/100 (higher than 93% of 1,761 Finance servers); tools 9 (the typical Finance server has 8); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Nota
Same job from other publishers: the closest match first, then the best rated.
ShumiCrypto market intelligence: prices, funding rates, narratives, regime, and delta-neutral research.not reviewedGrowingA- BlockrunWeb search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.not reviewedEstablishedB
- Yolfi Payments MCPLet AI agents add Yolfi crypto checkout, paylinks, webhooks, and status checks.not reviewedEstablishedA
- Pyth Pro MCP ServerReal-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.not reviewedEstablishedA
- EdgeDepth ResearchTest crypto-perpetual claims using recorded counts, baselines, and replay.not reviewedGrowingA
