Binance (security-first) + crypto analyst MCP server

Read from the package source without running it. The installed server may list more.

• _g
• binance_analyze_cycle

  Objective cycle-position inputs: Mayer Multiple (price/200d MA), drawdown from ATH (BTC only), distance to the next halving. Interpret with kb://frameworks/cycle-analysis — output a PHASE with uncertainty, never a target.

• binance_analyze_portfolio

  Values live balances; concentration; and — if the user provides their cost basis per asset (USDT) plus tax_rate/cashout_spread — per-asset PNL and the NET break-even (taxes+spread; local-currency effects excluded). No personal data is stored: everything is a parameter. Sizing doctrine: kb://discipline.

• binance_assess_risk

  Realized volatility (30/90d), max drawdown (90d window) and BTC correlation per asset — defaults to current non-stable holdings. Rehearse drawdowns BEFORE the market does it (kb://discipline rule 2).

• binance_backtest

  Light NO-LOOKAHEAD backtest of a simple rule (ema_cross/rsi_threshold).

• binance_backtest_dca

  Backtests a mechanical DCA plan on real history: invested, accumulated qty, avg cost, value now, PNL, honest lump-sum comparison and max drawdown. Simulation, NOT prediction — start-date sensitive (try several windows). Doctrine: kb://discipline.

• binance_backtest_harvest

  Backtests a pre-committed harvest grid ([{level, sell_pct}], pct of CURRENT holding, each level fires once on an upward daily-close crossing) vs pure hold. Simulation, NOT prediction. Doctrine: kb://discipline rule 4.

• binance_backtest_signal

  Backtests the layer-4 TECHNICAL composite signal on history (read-only, no lookahead, sentiment=0). Compare total_return_pct vs buy_hold_return_pct: any edge?

• binance_cancel_order_proposewrite action

  Proposes canceling an order (re-checks status; does NOT cancel).

• binance_cancel_order_statuswrite action

  Polls the outcome of a proposed cancellation (no side effects).

• binance_compute_indicators

  RSI/MACD/EMA/Bollinger/ATR over the klines (float values, candle-aligned).

• binance_generate_signal

  Transparent composite signal for a pair: direction + score + per-factor rationale + ATR risk levels. PROPOSES, never executes; every factor exposes its contribution. Note: our own out-of-sample walk-forward found NO robust edge (docs/research/) — treat signals as context, not as financial advice.

• binance_get_account_info

  Account info (canTrade, commissions; key permissions on mainnet only).

• binance_get_balance

  Spot balances with non-zero amounts (free/locked).

• binance_get_derivatives

  Public futures positioning for a pair: mark/index price, current funding rate, short funding history, open interest. THE leverage thermometer — interpret with the kb://glossary resource (funding, OI). No key permissions needed; on testnet this data is synthetic.

• binance_get_klines

  OHLCV candles for a pair/interval (Decimal values). limit <= 1000.

• binance_get_market_structure

  Whole-market context in one cheap call: Fear & Greed (+week series), BTC dominance, total market cap, BTC ATH/drawdown, on-chain fees and hashrate. Free public sources; any block may be None if its source is down (see notes). Interpret with kb://frameworks/cycle-analysis and kb://glossary.

• binance_get_news

  Crypto news from RSS feeds (CoinDesk, crypto.news), filterable by asset/source.

• binance_get_open_orders

  Open orders (all, or for one symbol).

• binance_get_order_book_depthwrite action

  Executable order-book liquidity audit: touch spread (bps), ±1% depth (USDT), thin-book warning, and 24h quote volume (IMPROVEMENTS.MD §4).

• binance_get_order_historywrite action

  Order history for a symbol (limit 1-1000).

• binance_get_price

  Current price for a symbol (e.g. BTCUSDT).

• binance_get_sentiment

  RAW aggregated sentiment for an asset over a window (lexicon-based, NOT a prediction).

• binance_get_ticker_24h

  Rolling 24h stats (change %, high/low, volume, last price).

• binance_scan_signals

  Signals for a watchlist, ranked by score (where to LOOK, not auto-trading).

• binance_spot_order_proposewrite action

  Proposes a spot order to the confirmer (does NOT execute). Returns intent_id.

• binance_spot_order_statuswrite action

  Polls the outcome of a proposed order (no side effects).

• Code scan71 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 3 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

83/100

higher than 75% of 1,765 Finance servers

Tools

27

the typical Finance server has 8

Tools that change things

22%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

4

more than 85% of 944 Finance servers

Downloads a week

101

more than 69% of 413 Finance servers with a package

Binance (security-first) + crypto analyst: common questions

Is Binance (security-first) + crypto analyst MCP server safe?

Mostly: it is graded B (83/100). Read the Binance (security-first) + crypto analyst safety report

How do I install Binance (security-first) + crypto analyst?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Binance (security-first) + crypto analyst need an API key?

Yes. The registry entry asks for BINANCE_READ_API_KEY, BINANCE_READ_API_SECRET.

Is Binance (security-first) + crypto analyst maintained?

The last commit was 9 days ago (2026-10-24). The latest release is v1.2.2.

What can I use instead of Binance (security-first) + crypto analyst?

Servers from other publishers that do the same job: AlgoVault — Crypto Quant Trade Calls MCP server, Blockrun MCP server and CoinRithm Agent Trading MCP server.

How does Binance (security-first) + crypto analyst compare with other Finance MCP servers?

safety score 83/100 (higher than 75% of 1,765 Finance servers); tools 27 (the typical Finance server has 8); tools that change things 22% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.