hyperliquid

The Hyperliquid MCP Server exposes a suite of MCP-enabled tools that let Claude Desktop interact with the Hyperliquid DEX through natural language commands. Once running, the server provides access to trading operations (placing and managing orders), account management (positions, balances, and orders), and market data (live and historical). You can trade with natural language, fetch real-time market data, monitor positions, and automate strategies using Claude's context-aware prompts. The available methods map directly to the 27 tools categorized into Trading, Account Management, Market Data, and Real-time WebSocket subscriptions, enabling workflows from simple market orders to complex multi-step strategies.

Prerequisites:

• Python 3.8+ installed
• Claude Desktop installed
• A Hyperliquid account with API credentials
• macOS, Linux, or Windows

Installation steps (automatic):

1. Clone the repository and navigate to it:

git clone https://github.com/seu-usuario/hyperliquid-mcp-server.git
cd hyperliquid-mcp-server

2. Run the setup script to install dependencies and generate configuration:

python3 setup.py

3. Create and edit the environment file with your credentials (example):

# .env example (place in project root or as instructed by setup)
HYPERLIQUID_PRIVATE_KEY=0x...
HYPERLIQUID_ACCOUNT_ADDRESS=0x...
HYPERLIQUID_NETWORK=mainnet

4. Ensure Claude Desktop is configured to connect to this MCP server by adding it to Claude's MCP configuration with the following mapping:

{
  "mcpServers": {
    "hyperliquid": {
      "command": "python",
      "args": ["server.py"],
      "env": {
        "HYPERLIQUID_PRIVATE_KEY": "your_private_key",
        "HYPERLIQUID_ACCOUNT_ADDRESS": "your_account_address",
        "HYPERLIQUID_NETWORK": "mainnet"
      }
    }
  }
}

Manual alternative (advanced):

# 1. Create a virtual environment
python3 -m venv venv

# 2. Activate the environment
# macOS/Linux:
source venv/bin/activate
# Windows:
venv\Scripts\activate

# 3. Install dependencies
pip install -r requirements.txt

# 4. Copy environment template and edit
cp .env.example .env
nano .env

5. Start the MCP server (example):

python server.py

6. In Claude Desktop, verify available tools:

Quais ferramentas da Hyperliquid você tem disponíveis?

Tips & notes:

• Keep credentials safe; store them only in the .env file and do not commit it to version control.
• Use a testnet or sandbox environment when first experimenting with trading commands.
• The MCP server exposes 27 tools divided into Trading, Account Management, Market Data, and WebSocket subscriptions. Familiarize yourself with the tool names like place_order, get_positions, get_candles, subscribe_market_data, etc., to compose effective prompts.
• If you encounter connection issues, check that HYPERLIQUID_NETWORK matches the network you intend to use and that the API keys have the required permissions.
• For production deployments, consider running the server behind a process manager and securing environment variables through a secrets manager.
• Review rate limits and implement basic error handling in your Claude prompts to handle transient API constraints gracefully.