mcpField
H
hyperliquid-mcp

hyperliquid-mcp

Remote
hyperliquid.mcp.junct.devFinance0Updated 30w ago
RepositoryVisit website

About hyperliquid-mcp

hyperliquid-mcp provides Hyperliquid API endpoints to AI agents through a hosted MCP server. Its tools are generated from the API specification, with each tool corresponding to an endpoint.

Key features

  1. 012 tools for Hyperliquid API endpoints
  2. 02Hosted Streamable HTTP endpoint
  3. 03No authentication or API key required
  4. 04Tools map 1:1 to API endpoints

Use cases

  1. 01Access Hyperliquid API endpoints from an MCP client
  2. 02Use Hyperliquid data in AI agent workflows

MCP support

The hosted MCP server exposes Hyperliquid API endpoints as tools to MCP clients. It uses Streamable HTTP and requires no authentication.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://hyperliquid.mcp.junct.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Hyperliquid MCP Server

MCP server for Hyperliquid. Agent-ready API for Hyperliquid.

Hosted at hyperliquid.mcp.junct.dev/mcp. Free to use. No auth. No API key required.

Part of Junct — the agent-readiness layer for web3.

Quick Start

Add to your MCP client config (Claude Desktop, Cursor, Windsurf):

{
  "mcpServers": {
    "hyperliquid": {
      "url": "https://hyperliquid.mcp.junct.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

About

This MCP server is deterministically generated from the Hyperliquid API specification. Every tool maps 1:1 to a real API endpoint — no hallucinated endpoints.

Links

Keywords: Hyperliquid, MCP server, DeFi, AI agent, agent-ready API, crypto tools, Model Context Protocol

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.