Hyperliquid MCP Server
# Hyperliquid MCP Server
An MCP server implementation that integrates the Hyperliquid SDK.
## Tools
- **get_all_mids**
- Retrieve mid prices for all coins on Hyperliquid
- No required inputs
- **get_candle_snapshot**
- Get historical candlestick data for any token
- Inputs:
- `coin` (string): Token symbol
- `interval` (string): Time interval (e.g., '15m', '1h')
- `startTime` (number): Start time in milliseconds since epoch
- `endTime` (number, optional): End time in milliseconds since epoch
- **get_l2_book**
- Access the L2 order book for any token
- Inputs:
- `symbol` (string): Token symbol
### Usage with Claude Desktop
Add this to your `claude_desktop_config.json`:
### NPX
```json
{
"mcpServers": {
"brave-search": {
"command": "npx",
"args": ["-y", "@mektigboy/server-hyperliquid"]
}
}
}
```
## License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: get_all_mids retrieves mid prices for all coins, get_candle_snapshot provides candlestick data for a specific token, and get_l2_book fetches the L2 order book for a token. There is no overlap or ambiguity in functionality, making tool selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern with 'get_' as the prefix, followed by a descriptive noun phrase (e.g., get_all_mids, get_candle_snapshot, get_l2_book). This uniformity enhances readability and predictability across the tool set.
With only 3 tools, the server feels thin for a trading or market data domain, which typically involves more operations like placing orders, checking balances, or managing positions. While the tools are well-defined, the count is borderline low for comprehensive coverage of such a scope.
The tool set is severely incomplete for a trading platform server, as it lacks essential operations such as order placement, account information retrieval, trade execution, or portfolio management. This creates significant gaps that will likely cause agent failures in real-world trading scenarios.