# com.bykaranteli/mcp (npm · bykaranteli-mcp)

Live crypto data: funding rates, funding arbitrage, OI pressure, Fear & Greed. Free, no API key.

- Trust score: 70/100 (medium)
- Change this week: +24
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `bykaranteli-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/com-bykaranteli-mcp/bykaranteli-mcp.md), [page](https://verifymcp.io/servers/com-bykaranteli-mcp/bykaranteli-mcp)

## Channel facts

- Registry: `npm`
- Package: `bykaranteli-mcp`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1059 tokens (~105/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add com-bykaranteli-mcp -- npx -y bykaranteli-mcp
```

### Codex

```bash
codex mcp add com-bykaranteli-mcp -- npx -y bykaranteli-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-bykaranteli-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "bykaranteli-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-bykaranteli-mcp --command npx --arg -y --arg bykaranteli-mcp
```

### Hermes

```yaml
mcp_servers:
  com-bykaranteli-mcp:
    command: "npx"
    args: ["-y", "bykaranteli-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "com-bykaranteli-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "bykaranteli-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 69, +40)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Maintenance: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] License: pass → unverified
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-08-01 (score 29, +6)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Schema quality: 783 → 1059
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 23, −23)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security] First check of Stability: unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] First check of Capabilities: unverified
- [functional] Licence: MIT
- [functional] Package version: 0.1.1 → 0.2.0
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 46, +22)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 24, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (10)

### `get_market_indices` (~59 tokens)

Crypto market indices (Fear & Greed, BTC dominance, euphoria)

Call this when the user asks about overall crypto market sentiment or macro state: the Fear & Greed index (today and yesterday), Bitcoin dominance percentage, total market cap, or the Retail Euphoria composite. Live values refreshed about every 30 minutes.

### `get_liquidations` (~145 tokens)

Crypto liquidations: daily long/short totals per symbol and exchange

Call this when the user asks how much was liquidated in crypto futures, whether longs or shorts got flushed, or for liquidation history. Returns daily long and short liquidation totals in USD per symbol and exchange, recorded from ByKaranteli's own Binance, Bybit and OKX stream collectors (recorded events, a floor, not estimates). One row per finalized UTC day, symbol and exchange; history begins 2026-07-30 and grows daily.

Input parameters:

- `days` (integer): How many most recent days to return (default 7).
- `symbol` (string): Optional symbol filter like BTCUSDT or ETHUSDT. Omit for all symbols.

### `get_etf_flows` (~131 tokens)

US spot Bitcoin and Ethereum ETF daily flows

Call this when the user asks about Bitcoin or Ethereum ETF flows: daily net inflows or outflows, cumulative flow since launch, or total net assets of the US spot ETFs (IBIT, FBTC, ETHA and the rest). Returns one row per finalized US trading day and asset with net inflow, total net assets, cumulative inflow and value traded, all in USD. About 14 months of history.

Input parameters:

- `asset` (string): Filter to one asset. Omit for both.
- `days` (integer): How many most recent trading days to return (default 10).

### `get_funding_heatmap` (~135 tokens)

Funding rates across top-30 Binance perps

Call this when the user asks for the full current funding table across the top-30 Binance perp universe, or the funding rate of one specific coin. For a pre-ranked top-10 of the most extreme funding rates, use get_top_movers instead. Returns per-symbol funding rate (per settlement interval), 24h open interest change and 24h price change for the top-30 Binance USDT-M perpetuals. Positive funding means longs pay shorts.

Input parameters:

- `symbol` (string): Optional. Filter to one symbol, e.g. BTCUSDT or just BTC. Omit to get all 30 rows.

### `get_funding_arbitrage` (~89 tokens)

Cross-exchange funding arbitrage opportunities

Call this when the user asks about funding arbitrage, funding rate differences between exchanges, or delta-neutral carry trades. Compares funding across Binance, OKX, Bybit, Gate, HTX and BingX for 12 major perps and returns the best long/short venue per symbol with gross and net annualized APR (net of taker fees and weekly rebalance cost).

### `get_pressure_scores` (~160 tokens)

Derivatives pressure scores (funding + OI + basis composite)

Call this when the user asks which coins are crowded or over-leveraged, or asks for the pressure/derivatives-stress score of specific coins. For a quick top-10 ranking of the highest-stress coins right now, use get_top_movers instead. Each symbol gets a 0-100 composite score built from funding rate, 1h/4h/24h open interest deltas and basis, with a LONG/SHORT/NEUTRAL direction and a plain-language regime label.

Input parameters:

- `limit` (integer): Optional. Max rows to return when no symbol filter is set (default 20, sorted by score).
- `symbol` (string): Optional. Return only this symbol, e.g. BTCUSDT or BTC.

### `get_top_movers` (~59 tokens)

Top movers: OI spikes, extreme funding, widest basis, highest stress

Call this when the user asks what is moving in crypto derivatives right now, which coins have the biggest open interest changes, the most extreme funding, the widest basis, or the highest derivatives stress. Returns four top-10 lists in one call.

### `get_recent_signals` (~99 tokens)

Recent closed trading signals with verified outcomes

Call this when the user asks how the ByKaranteli signal engine is doing today, or wants recent closed LONG/SHORT signals with real outcomes (TP1, SL or TIMEOUT) and net basis-point results. Includes a 24h summary (wins, losses, net bps). Every signal is published with a SHA-256 receipt and results are net of fees, slippage and funding; live signals only, never backtests.

### `get_symbol_performance` (~125 tokens)

Per-symbol signal performance and recent trades

Call this when the user asks how signals performed on a specific coin (win rate, profit factor, net PnL, best/worst trade) or wants that coin's recent closed signals. Data is the live verified track record for one Binance USDT-M perp over a 30, 90 or 180 day window.

Input parameters:

- `symbol` (string, required): The symbol, e.g. BTCUSDT, or a coin name like BTC.
- `window_days` (number): Optional lookback window in days (30, 90 or 180). Default 90.

### `get_strategy_leaderboard` (~57 tokens)

Strategy leaderboard with verified live results

Call this when the user asks which trading strategies are performing best, or wants win rate, profit factor, drawdown and Sharpe per strategy. Rankings are computed from live closed signals only (no backtests), net of fees.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-bykaranteli-mcp/bykaranteli-mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 69
- 2026-08-01: 29
- 2026-07-31: 23
- 2026-07-30: 46
- 2026-07-28: 24
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/bykaranteli-mcp
- Socket report: https://socket.dev/npm/package/bykaranteli-mcp
- Repository: https://github.com/bykarantelicom/bykaranteli-mcp
- Website: https://bykaranteli.com/developers
- Changelog RSS feed: https://verifymcp.io/servers/com-bykaranteli-mcp/bykaranteli-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-bykaranteli-mcp/bykaranteli-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-bykaranteli-mcp/bykaranteli-mcp