Hyperliquid MCP for HL Coder
Hyperliquid MCP Server for HL Coder
TradingBalthazar
README
Hyperliquid MCP for HL Coder
This repository contains a Model Context Protocol (MCP) server for Hyperliquid that integrates with HL Coder. It allows you to interact with Hyperliquid through natural language in HL Coder.
Quick Start
To install and run the Hyperliquid MCP server, simply run the following command in HL Coder:
curl -s https://raw.githubusercontent.com/TradingBalthazar/hyperliquid-mcp-v2/main/install-and-run.sh | bash
This will:
- Download and install the necessary files
- Install the required dependencies
- Start the Hyperliquid MCP server
- Open a dashboard in your browser to enter your credentials
Features
- Connect to Hyperliquid using your secret key
- Get market data (prices, order books, etc.)
- Get user data (positions, account value, etc.)
- Place and cancel orders
- Update leverage
Setup
- Run the installation command in HL Coder
- When the dashboard opens in your browser, enter your Hyperliquid secret key
- (Optional) Enter your Ethereum account address
- Select the network (mainnet or testnet)
- Click "Connect to Hyperliquid"
Example Commands
Once connected, you can use natural language to interact with Hyperliquid in HL Coder. Here are some examples:
- "Get current market prices for all coins"
- "Show my current positions and account value"
- "Place a limit buy order for 0.1 BTC at $60,000"
- "Cancel all my open orders for ETH"
- "Update my leverage for BTC to 5x"
Available Tools
The Hyperliquid MCP server provides the following tools:
get_market_data
Get market data from Hyperliquid.
Parameters:
dataType
: Type of market data to retrieve (all_mids, l2_snapshot, meta, meta_and_asset_ctxs, spot_meta, spot_meta_and_asset_ctxs, candles, funding_history)coin
: Coin symbol (required for l2_snapshot, candles, funding_history)interval
: Candle interval (required for candles)startTime
: Start time in milliseconds (required for candles, funding_history)endTime
: End time in milliseconds (optional for candles, funding_history)
get_user_data
Get user-specific data from Hyperliquid.
Parameters:
dataType
: Type of user data to retrieve (user_state, spot_user_state, open_orders, frontend_open_orders, user_fills, user_fills_by_time, user_funding_history, user_fees, user_staking_summary, user_staking_delegations, user_staking_rewards, query_sub_accounts)startTime
: Start time in milliseconds (required for user_fills_by_time, user_funding_history)endTime
: End time in milliseconds (optional for user_fills_by_time, user_funding_history)
place_limit_order
Place a limit order on Hyperliquid.
Parameters:
coin
: Coin symbolisBuy
: Whether the order is a buysize
: Order sizeprice
: Order pricetimeInForce
: Time in force (Gtc, Ioc, Alo)reduceOnly
: Whether the order is reduce-onlyclientOrderId
: Client order ID
place_market_order
Place a market order on Hyperliquid.
Parameters:
coin
: Coin symbolisBuy
: Whether the order is a buysize
: Order sizeslippage
: Slippage tolerance (default: 0.05)clientOrderId
: Client order ID
cancel_order
Cancel an order on Hyperliquid.
Parameters:
coin
: Coin symbolorderId
: Order IDclientOrderId
: Client order ID
update_leverage
Update leverage for a coin.
Parameters:
coin
: Coin symbolleverage
: Leverage valueisCross
: Whether to use cross margin (default: true)
Available Resources
The Hyperliquid MCP server provides the following resources:
hyperliquid://market/all-mids
: Current mid prices for all coinshyperliquid://market/l2-book/{coin}
: L2 order book for a specific coinhyperliquid://user/{address}/state
: User state for a specific addresshyperliquid://user/{address}/open-orders
: Open orders for a specific address
Security
Your secret key is stored locally and is only used to authenticate with Hyperliquid. It is never sent to any third-party servers.
Requirements
- Node.js 14+
- Python 3.6+
- pip (for installing Python dependencies)
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.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.