Hyperliquid MCP Server
MCP server for Hyperliquid perpetual DEX with 48 tools for trading, monitoring, risk management, and security. Enables real-time market data, order management, risk validation, and automated trading strategies.
README
Hyperliquid MCP Server š
Model Context Protocol (MCP) server for Hyperliquid ā 48 tools for trading, monitoring, risk management, and security on the Hyperliquid perpetual DEX.
Built on the official hyperliquid-python-sdk with production-grade error handling.
Features
š” Tier 1 ā Monitoring (15 tools)
- Real-time user state, positions, balances
- Open orders, trade history, funding history
- Market data: mid prices, L2 order book, candlesticks
- Sub-accounts, staking, fee structure
š¹ Tier 2 ā Trading (10 tools)
- Limit, market, and trigger orders
- Bracket orders (entry + TP + SL)
- Position management: modify, close, leverage
- Funding rate impact calculator
ā ļø Tier 3 ā Risk Management (10 tools)
- Order risk validation before execution
- Liquidation price estimation
- Margin health monitoring
- Portfolio health check & simulation
- Auto leverage adjustment
š Tier 4 ā Security (8 tools)
- Wallet & configuration validation
- Preflight checks before trading
- API Wallet / Agent Mode setup
- Trading limits, rate limiting
- Audit trail & emergency stop
š Bonus Analytics (5 tools)
- Position analysis with P&L and risk scoring
- Performance metrics (win rate, Sharpe, drawdown)
- Multi-coin comparison
- Strategy backtesting (MA/RSI/Momentum)
- Market sentiment analysis
Quick Start
1. Install
git clone https://github.com/samimiair/hyperliquid-mcp.git
cd hyperliquid-mcp
pip install -r requirements.txt
2. Configure
cp .env.example .env
# Edit .env with your wallet details:
# HYPERLIQUID_PRIVATE_KEY=your_64_char_hex_key
# HYPERLIQUID_ACCOUNT_ADDRESS=0xYourWalletAddress
3. Run
./run.sh
Or run directly with Hermes:
hermes mcp add hyperliquid --command /path/to/hyperliquid-mcp/run.sh
hermes config set mcp_servers.hyperliquid.cwd /path/to/hyperliquid-mcp
hermes config set mcp_servers.hyperliquid.timeout 120
Environment Variables
| Variable | Required | Description |
|---|---|---|
HYPERLIQUID_PRIVATE_KEY |
ā | Your wallet private key (64 hex chars) |
HYPERLIQUID_ACCOUNT_ADDRESS |
ā | Your wallet address (0x...) |
HYPERLIQUID_API_WALLET |
ā | API wallet for Agent Mode |
HYPERLIQUID_TESTNET |
ā | Set to "true" for testnet (default: mainnet) |
Architecture
hyperliquid-mcp/
āāā main.py # MCP server entry point (48 tools)
āāā api_client.py # Hyperliquid API wrapper (SDK-based)
āāā trading.py # Order placement & management
āāā monitoring.py # Market data & state queries
āāā risk_mgmt.py # Risk validation & simulation
āāā security.py # Wallet & configuration checks
āāā validators.py # Input validation
āāā rate_limiter.py # API rate limiting
āāā alert_manager.py # Error & alert handling
āāā wallet.py # (Deprecated) Legacy wallet code
āāā run.sh # Startup script with env validation
āāā .env.example # Configuration template
āāā requirements.txt # Dependencies
Security
- Never commit your
.envfile ā it's in.gitignore - All secrets are read from environment variables
- The
run.shscript validates required env vars before starting - Use API Wallet / Agent Mode to limit trading permissions
- Emergency stop tool (
emergency_stop) closes all positions instantly
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.