Skip to main content
Glama
hyperliquid-whalealert-mcp

hyperliquid-whalealert-mcp

by kukapay

Hyperliquid WhaleAlert MCP

An MCP server that provides real-time whale alerts on Hyperliquid, flagging positions with a notional value exceeding $1 million.

GitHub License Python Version Status

Features

  • Tool: get_whale_alerts: Fetches recent whale transactions and returns them as a Markdown table using pandas for clean formatting.

  • Prompt: summarize_whale_activity: Generates a summary of whale transactions, including metrics like total position value and notable symbols.

Related MCP server: hyperliquid-info-mcp

Prerequisites

  • Python: Version 3.10 or higher.

  • CoinGlass API Key: Obtain from CoinGlass (required for API access).

  • uv: Package and dependency manager (install uv).

Installation

  1. Clone the Repository:

    git clone https://github.com/kukapay/hyperliquid-whalealert-mcp.git
    cd hyperliquid-whalealert-mcp
  2. Install Dependencies:

    uv sync

    This installs dependencies specified in pyproject.toml.

  3. Claude Desktop Integration: Install the server in Claude Desktop:

    uv run mcp install mcp.py --name "Hyperliquid Whale Alert"

    Or update the configuration file manually:

    {
      "mcpServers": {
        "hyperliquid-whalealert": {
          "command": "uv",
          "args": [ "--directory", "/path/to/hyperliquid-whalealert-mcp", "run", "main.py" ],
          "env": { "COINGLASS_API_KEY": "your_api_key" }
        }
      }
    }

    Replace /path/to/hyperliquid-whalealert-mcp with your actual installation path and COINGLASS_API_KEY with your API key.

Usage

Using the Tool

The get_whale_alerts tool fetches whale transaction data and returns it as a Markdown list. Example output:

- **ETH Transaction**:
  - User Address: 0x3fd4444154242720c0d0c61c74a240d90c127d33
  - Position Size: 12700
  - Entry Price: $1611.62
  - Liquidation Price: $527.2521
  - Position Value (USD): $21003260
  - Action: Close
  - Create Time: 2025-05-20 12:31:57
- **BTC Transaction**:
  - User Address: 0x1cadadf0e884ac5527ae596a4fc1017a4ffd4e2c
  - Position Size: 33.54032
  - Entry Price: $87486.2
  - Liquidation Price: $44836.8126
  - Position Value (USD): $2936421.4757
  - Action: Close
  - Create Time: 2025-05-20 12:31:17

To invoke the tool:

  • In the MCP Inspector, select get_whale_alerts and execute.

  • In Claude Desktop, use the registered server and call the tool via the UI or API.

Using the Prompt

The summarize_whale_activity prompt generates a summary of whale transactions. Example interaction (in a compatible client):

/summarize_whale_activity

Response:

I'll analyze the whale transaction data and provide a summary.

This can be extended by LLMs to provide detailed metrics like total position value or notable symbols.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Available Tools

1 tool
get_whale_alertsB

Fetch recent whale alerts and return as a Markdown table

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as fetching whale alerts, making it distinct by default.

    Naming Consistency5/5

    The single tool follows a clear verb_noun pattern (get_whale_alerts), which is consistent and predictable. Since there are no other tools to compare against, naming is inherently consistent.

    Tool Count2/5

    A single tool is too few for the server's apparent purpose of monitoring whale alerts, as it lacks operations like filtering, subscribing, or historical queries. This minimal scope limits functionality and may cause agent failures due to incomplete coverage.

    Completeness2/5

    The tool surface is severely incomplete for a whale alert system, offering only fetching recent alerts without capabilities such as filtering by criteria, accessing historical data, or managing alerts. This creates significant gaps that will hinder agent workflows.

    Related MCP Connectors

    Related MCP Servers