Coinversaa Pulse

Coinversaa Pulse

Provides comprehensive crypto intelligence for the Hyperliquid exchange, allowing users to query trader profiles, behavioral cohorts, and live market data. It enables AI agents to analyze over 1.8 billion trades, track whale positions, and access real-time liquidation heatmaps.

Category
访问服务器

README

Coinversaa Pulse — MCP Server

<a href="https://glama.ai/mcp/servers/@Coinversaa/mcp-server"><img width="380" height="200" src="https://glama.ai/mcp/servers/@Coinversaa/mcp-server/badge" alt="Coinversaa Pulse MCP Server" /></a>

Crypto intelligence for AI agents. Query 710K+ Hyperliquid wallets, 1.8B+ trades, behavioral cohorts, and live market data through any MCP-compatible client.

Quick Start

1. Get an API Key

Request an API key at coinversaa.ai/developers or email chat@coinversaa.ai.

2. Configure Your MCP Client

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "coinversaa": {
      "command": "npx",
      "args": ["-y", "@coinversaa/mcp-server"],
      "env": {
        "COINVERSAA_API_KEY": "cvsa_your_key_here"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "coinversaa": {
      "command": "npx",
      "args": ["-y", "@coinversaa/mcp-server"],
      "env": {
        "COINVERSAA_API_KEY": "cvsa_your_key_here"
      }
    }
  }
}

Claude Code

claude mcp add coinversaa -- npx -y @coinversaa/mcp-server

Set the env var in your shell:

export COINVERSAA_API_KEY="cvsa_your_key_here"

That's it. No cloning, no building — npx handles everything.

Available Tools (26)

Pulse — Trader Intelligence

Tool Description
pulse_global_stats Total traders, trades, volume, PnL across Hyperliquid
pulse_market_overview Live prices, funding rates, OI for every pair
pulse_leaderboard Top traders ranked by PnL, win rate, volume, score, or risk-adjusted returns
pulse_hidden_gems Underrated high-performers most platforms miss
pulse_most_traded_coins Most actively traded coins ranked by volume and trade count
pulse_biggest_trades Biggest winning or losing trades across all of Hyperliquid
pulse_recent_trades Biggest trades in the last N minutes/hours
pulse_token_leaderboard Top traders for a specific coin

Pulse — Trader Profiles

Tool Description
pulse_trader_profile Full due diligence on any wallet (PnL, win rate, tiers, profit factor)
pulse_trader_performance 30-day vs all-time comparison with trend direction
pulse_trader_trades Recent trades for any wallet — the copy-trading signal
pulse_trader_daily_stats Day-by-day PnL, win rate, and volume breakdown
pulse_trader_token_stats Per-coin P&L breakdown (find a trader's edge)
pulse_trader_closed_positions Historical position lifecycle — entry/exit prices, hold duration, PnL
pulse_trader_closed_position_stats Aggregate stats: avg hold time, position win rate, scalper vs swing

Pulse — Cohort Intelligence

Tool Description
pulse_cohort_summary Behavioral tier breakdown across 710K+ wallets
pulse_cohort_positions What money_printers / whales are holding RIGHT NOW
pulse_cohort_trades Every trade a cohort made in the last N minutes/hours
pulse_cohort_history Historical performance trends for any cohort

Market — Live Data

Tool Description
market_price Current mark price for any symbol
market_positions Open positions for any wallet
market_orderbook Bid/ask depth for any trading pair

Live — Real-Time Analytics

Tool Description
live_liquidation_heatmap Liquidation clusters across price levels — support/resistance signals
live_long_short_ratio Global or per-coin long/short ratio with optional history
live_cohort_bias Net long/short stance for every tier on a given coin
pulse_recent_closed_positions Positions just closed across all traders with entry/exit data

Example Prompts

Once connected, try asking your AI:

  • "What are the top 5 traders on Hyperliquid by PnL?"
  • "Show me what the money_printer tier is holding right now"
  • "What are the biggest trades in the last 10 minutes?"
  • "What did wallet 0x7fda...7d1 trade in the last hour?"
  • "Find underrated traders with 70%+ win rate"
  • "Do a deep dive on wallet 0x7fda...7d1 — are they still performing?"
  • "Where are the BTC liquidation clusters?"
  • "Are smart money traders long or short ETH right now?"
  • "Show me the biggest losses in the last 24 hours"
  • "What coins are most actively traded right now?"
  • "What's this trader's average hold time and position win rate?"

Environment Variables

Variable Required Default Description
COINVERSAA_API_KEY Yes Your API key (starts with cvsa_)
COINVERSAA_API_URL No https://staging.api.coinversaa.ai API base URL (will move to api.coinversaa.ai for production)

Development

git clone https://github.com/coinversaa/mcp-server.git
cd mcp-server
npm install
npm run build

# Test with MCP Inspector
npx @modelcontextprotocol/inspector build/index.js

What Makes This Different

This isn't a wrapper around a public blockchain API. Coinversaa indexes Hyperliquid's clearinghouse directly and computes analytics that don't exist anywhere else:

  • Behavioral cohorts: 710K wallets classified into PnL tiers (money_printer to giga_rekt) and size tiers (leviathan to shrimp)
  • Live cohort positions: See what the best traders are holding in real-time
  • Real-time trade feed: Every trade by any wallet or cohort, queryable by time window
  • Liquidation heatmaps: Cluster analysis across price levels for any coin
  • Closed position analytics: Full position lifecycle with hold duration and entry/exit analysis
  • Hidden gem discovery: Find skilled traders that ranking sites miss
  • 1.8B+ trades indexed: The deepest Hyperliquid dataset available as an API

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT


Built by Coinversaa

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