- Home
- MCP servers
- Hyperliquid
Hyperliquid
- python
6
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
You deploy this MCP server to provide real-time trading data through an MCP-compliant API and an interactive dashboard. It offers live market prices, recent trades, candlestick charts, an order book, and funding rates, all accessible via standardized MCP endpoints and a Gradio-based UI for visualization.
How to use
Connect to the MCP-enabled endpoints from your client or automation tool to retrieve live market data, execute trading tools, and display visualizations. Use the HTTP MCP endpoint to call tools and monitor health, or run the local Python server or Docker container to host the MCP server yourself. The dashboard provides interactive tabs for Market Prices, Recent Trades, Candlestick Charts, Order Book, and Funding Rates for seamless exploration and integration.
How to install
Prerequisites: you need Python 3.8+ or Docker installed on your system.
Option 1: Run locally with Python
# Clone the project
git clone https://huggingface.co/spaces/rzvn/hyperliquid-mcp-server
cd hyperliquid-mcp-server
# Install dependencies
pip install -r requirements.txt
# Run locally (start the MCP server and dashboard)
python app.py
Access points after starting locally:
Gradio Dashboard: http://localhost:7860 MCP API: http://localhost:3001
Additional configuration and run options
Option 2: Run with Docker
docker build -t hyperliquid-mcp .
docker run -p 7860:7860 -p 3001:3001 hyperliquid-mcp
Notes on usage patterns
- The MCP API exposes health checks and tool endpoints that you can call from your MCP client. - The Gradio dashboard provides live visualizations for the five trading tools. - Use the HTTP endpoint for remote calls and the local stdio command for development or testing workflows.
Configuration and endpoints
This server supports both an HTTP MCP endpoint and a local stdio runtime. The HTTP endpoint is used by remote clients to call MCP tools. The local stdio runtime runs the Python server process on your machine.
Available tools
get_all_mids
Fetch real-time mid prices for all available trading pairs (live market prices).
get_recent_trades
Retrieve the most recent trades for a given symbol with control over the number of trades returned.
get_candles
Provide candlestick data for selected symbol and timeframe with configurable candle count.
get_order_book
Return live bid/ask depth information for a specified symbol.
get_funding_rates
Return current and historical funding rates for perpetual contracts.