QuantXData MCP Server

QuantXData MCP Server

MCP server that exposes QuantXData's institutional crypto market data APIs to AI assistants, enabling natural language queries for trades, order books, OHLCV, options, and more across 120+ exchanges.

Category
访问服务器

README

QuantXData MCP Server

Model Context Protocol (MCP) server for QuantXData API - the first institutional crypto data provider with AI-native access.

What is This?

This MCP server exposes all QuantXData market data APIs to AI assistants like Claude Desktop, allowing you to query institutional-grade crypto data using natural language - no coding required.

Example queries:

  • "Get 24h volume for BTC/USDT on Binance"
  • "Show me order book depth for ETH across top 5 exchanges"
  • "Compare funding rates for BTC perpetuals on Binance and Deribit"
  • "Fetch daily OHLCV for SOL/USDT since January 2024"

Features

  • 12 API Tools: Complete access to QuantXData's market data endpoints
  • AI-Native: Query crypto data using natural language via Claude, ChatGPT, or any MCP-compatible tool
  • Institutional Grade: Full tick history, sub-millisecond timestamps, 120+ exchanges
  • Zero Code: No API integration required - just ask your AI assistant

Supported Data

  • Trades: Historical trade executions with microsecond precision
  • Order Books: L1 top-of-book and L2 snapshots
  • OHLCV: Aggregated candlestick data (1m, 15m, 1h, 1d)
  • Options: Greeks (delta, gamma, vega, theta) and implied volatility
  • Multi-Exchange: Consolidated data across 120+ venues
  • Real-Time: WebSocket-style streams (polling-based)

Installation

Prerequisites

  • Node.js 18+
  • QuantXData API credentials (email + signing key)

Quick Start with Claude Desktop

  1. Install the server:
npx -y @quantxdata/mcp-server
  1. Configure Claude Desktop:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%\Claude\claude_desktop_config.json

Add this configuration:

{
  "mcpServers": {
    "quantxdata": {
      "command": "npx",
      "args": ["-y", "@quantxdata/mcp-server"],
      "env": {
        "QUANTXDATA_EMAIL": "your-email@example.com",
        "QUANTXDATA_SIGNING_KEY": "your-signing-key-here"
      }
    }
  }
}
  1. Restart Claude Desktop

  2. Test it:

Ask Claude: "Use QuantXData to get the last 10 BTC/USDT trades from Binance"

API Credentials

Get your API credentials at quantxdata.ai:

  1. Sign up for a free account
  2. Generate your API signing key
  3. Add your email and key to the MCP config

Available Tools

1. get_instruments

List all supported exchanges and trading pairs (no auth required)

2. get_trades

Get historical trade executions

  • Parameters: exchange, instrument, from, to, limit
  • Example: "Get BTC/USDT trades from Binance for the last hour"

3. get_orderbooks

Get L1/L2 order book snapshots

  • Parameters: exchange, instrument, from, limit
  • Example: "Show order book depth for ETH/USD on Coinbase"

4. get_ohlcv

Get aggregated OHLCV candlestick data

  • Parameters: exchange, instrument, aggregation (1m/15m/1h/1d), from, to, limit
  • Example: "Get hourly candles for SOL/USDT on Binance"

5. get_multi_trades

Get consolidated trades across multiple exchanges

  • Parameters: exchanges, base_currencies, quote_currencies, from, to, limit
  • Example: "Compare BTC volume across Binance, Coinbase, and Kraken"

6. get_option_quotes

Get options Greeks and implied volatility

  • Parameters: exchange, instrument, from, to
  • Example: "Get BTC options data from Deribit"

7-9. get_histoday / get_histohour / get_histominute

Get historical OHLCV data (CryptoCompare-compatible format)

  • Parameters: fsym, tsym, e (exchange), aggregate, toTs, limit

10. get_ob_l1_top

Get L1 order book top-of-book (best bid/ask)

11. get_ob_l2_snapshot

Get L2 order book snapshot with configurable depth

12. stream_realtime

Get real-time market data (polling-based)

  • Parameters: exchange, instrument, stream_time (1-120 seconds)

VS Code / Cursor / Cline

Add to your MCP settings:

{
  "mcpServers": {
    "quantxdata": {
      "command": "npx",
      "args": ["-y", "@quantxdata/mcp-server"],
      "env": {
        "QUANTXDATA_EMAIL": "your-email@example.com",
        "QUANTXDATA_SIGNING_KEY": "your-signing-key-here"
      }
    }
  }
}

Authentication

The MCP server uses HMAC-SHA256 signing (same as QuantXData REST API):

  • Requests are signed with your email + signing key
  • Signatures are automatically generated for each API call
  • No manual token management required

Pricing

  • Free Tier: 1,000 API calls/month
  • Starter: $99/month, 100,000 calls
  • Pro: $499/month, 1M calls
  • Enterprise: Custom pricing, unlimited

See quantxdata.ai/pricing

Response Format

All tools return data in the same format as the QuantXData REST API:

  • Trades: space-delimited format for efficiency
  • OHLCV: JSON with open/high/low/close/volume
  • Order books: bids/asks arrays with price/quantity
  • Options: Greeks + IV in structured JSON

Examples

Cross-Exchange Volume Comparison

"Compare 24h BTC/USDT volume across Binance, Coinbase, and Kraken"

Funding Rate Analysis

"Get BTC perpetual funding rates from Binance and Deribit for the last 7 days"

Order Book Depth

"Show me L2 order book for ETH/USDT on Binance with 20 levels"

Options Analysis

"Get delta and IV for BTC options expiring this week on Deribit"

Troubleshooting

"Authentication failed"

  • Verify your email and signing key in the config
  • Check that your QuantXData account is active

"Rate limit exceeded"

  • Check your plan limits at quantxdata.ai/pricing
  • Upgrade your plan if needed

"Tool not found"

  • Restart your MCP client (Claude Desktop, VS Code, etc.)
  • Verify the server is running: check logs in the MCP client

Development

# Clone the repo
git clone https://github.com/appydam/quantxdata-mcp
cd quantxdata-mcp

# Install dependencies
npm install

# Build
npm run build

# Test locally
npm link

Support

License

MIT


Built for: Quant traders, algo developers, AI researchers
Maintained by: QuantXData
Learn more: quantxdata.ai

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选