What tools does Hyperliquid MCP Server provide?
It provides three tools: `get_all_mids` (retrieve mid prices for all coins), `get_candle_snapshot` (historical candlestick data), and `get_l2_book` (L2 order book for a token).
@mektigboy
Basic information
MCP Hyperliquid (https://app.hyperliquid.xyz) server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"brave-search": {
"command": "npx",
"args": [
"-y",
"@mektigboy/server-hyperliquid"
]
}
}
}Get mid prices for all coins on Hyperliquid
Get candlestick data for a token on Hyperliquid
Get the L2 book of a token on Hyperliquid
An MCP server implementation that integrates the Hyperliquid SDK to provide access to Hyperliquid exchange market data.
Configure it in Claude Desktop by adding the provided NPX command to your claude_desktop_config.json. Tools can then be invoked directly: get_all_mids (no inputs), get_candle_snapshot (requires coin, interval, startTime), and get_l2_book (requires symbol).
It provides three tools: `get_all_mids` (retrieve mid prices for all coins), `get_candle_snapshot` (historical candlestick data), and `get_l2_book` (L2 order book for a token).
Add the NPX configuration to your `claude_desktop_config.json` using `npx -y @mektigboy/server-hyperliquid`.
Data is retrieved directly from the Hyperliquid exchange through the official Hyperliquid SDK.
Yes, it is licensed under the MIT License, allowing free use, modification, and distribution.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Hindsight: Agent Memory That Learns
Comments