Hyperliquid MCP Updated

Hyperliquid MCP Updated

A read-only Model Context Protocol server for Hyperliquid that exposes over 30 tools to query public market data and user state via the Hyperliquid Info API, without requiring a private key.

Category
访问服务器

README

Hyperliquid MCP Updated

Read-only Model Context Protocol server for Hyperliquid using the official hyperliquid-python-sdk (see pyproject.toml). Use this when third-party MCP wrappers drift from the SDK.

Features

  • No private key — only public POST /info endpoints.
  • One MCP tool per Info HTTP method (all read-only SDK methods that call /info), plus hl_info_request for any extra documented type not yet wrapped.
  • Not included: WebSocket subscribe / unsubscribe, Exchange (signing / trading), and internal helpers like set_perp_meta.

Install

cd Hyperliquid-MCP-Updated
uv venv && source .venv/bin/activate   # or: python -m venv .venv
uv pip install -e .

Run (stdio, for MCP clients):

hyperliquid-mcp-updated

Environment

Variable Meaning
HL_TESTNET true / 1https://api.hyperliquid-testnet.xyz
HL_API_URL Override base URL entirely
HL_LOG_LEVEL Default WARNING

Cursor mcp.json

Local checkout (replace path):

{
  "mcpServers": {
    "hyperliquid-updated": {
      "command": "/Users/you/path/to/Hyperliquid-MCP-Updated/.venv/bin/hyperliquid-mcp-updated",
      "args": [],
      "env": {}
    }
  }
}

Or with uv (no venv path hardcoded):

{
  "mcpServers": {
    "hyperliquid-updated": {
      "command": "/Users/you/.local/bin/uv",
      "args": [
        "--directory",
        "/Users/you/path/to/Hyperliquid-MCP-Updated",
        "run",
        "hyperliquid-mcp-updated"
      ],
      "env": {}
    }
  }
}

After editing, reload MCP in Cursor settings.

Tools ↔ hyperliquid.info.Info (SDK)

MCP tool SDK method
hl_clearinghouse_state user_state
hl_spot_clearinghouse_state spot_user_state
hl_open_orders open_orders
hl_frontend_open_orders frontend_open_orders
hl_user_fills user_fills
hl_user_fills_by_time user_fills_by_time
hl_user_funding_history user_funding_history
hl_portfolio portfolio
hl_user_vault_equities user_vault_equities
hl_user_role user_role
hl_user_non_funding_ledger_updates user_non_funding_ledger_updates
hl_historical_orders historical_orders
hl_user_twap_slice_fills user_twap_slice_fills
hl_user_fees user_fees
hl_user_staking_summary user_staking_summary
hl_user_staking_delegations user_staking_delegations
hl_user_staking_rewards user_staking_rewards
hl_delegator_history delegator_history
hl_order_status_by_oid query_order_by_oid
hl_order_status_by_cloid query_order_by_cloid
hl_referral_state query_referral_state
hl_sub_accounts query_sub_accounts
hl_user_to_multi_sig_signers query_user_to_multi_sig_signers
hl_perp_deploy_auction_status query_perp_deploy_auction_status
hl_user_dex_abstraction query_user_dex_abstraction_state
hl_user_abstraction query_user_abstraction_state
hl_user_rate_limit user_rate_limit
hl_spot_deploy_auction_status query_spot_deploy_auction_status
hl_extra_agents extra_agents
hl_meta meta
hl_meta_and_asset_ctxs meta_and_asset_ctxs
hl_perp_dexs perp_dexs
hl_spot_meta spot_meta
hl_spot_meta_and_asset_ctxs spot_meta_and_asset_ctxs
hl_all_mids all_mids
hl_l2_book l2_snapshot
hl_candles candles_snapshot
hl_funding_history funding_history
hl_predicted_fundings (no SDK method)post(..., {"type":"predictedFundings"})
hl_active_asset_data (no SDK method)post(..., {"type":"activeAssetData", ...})
hl_info_request raw post("/info", {**payload, "type": request_type})

Publish to GitHub

cd Hyperliquid-MCP-Updated
git init
git remote add origin https://github.com/lucaluca-04/Hyperliquid-MCP-Updated.git
git add .
git commit -m "Initial hyperliquid-mcp-updated server"
git branch -M main
git push -u origin main

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选