Aster MCP Server
An MCP server for Aster Futures and Spot APIs, enabling AI agents to query market data, place orders, and check positions and accounts securely.
README
Aster MCP Server
An Model Context Protocol server for Aster Futures and Spot APIs, enabling AI agents (e.g. Cursor, Claude, LangChain) to securely query market data, place orders, and check positions and accounts.
Features
- Config & security: Multi-account, local Fernet-encrypted API key storage (
~/.config/aster-mcp/) - Auth: HMAC (API Key/Secret) and V3 key signing (EIP-712, user/signer/private_key; see aster-finance-futures-api-v3)
- MCP tools:
- Futures: Market data, account/positions, place/cancel orders, leverage & margin, transfers, income, commission rate, leverage bracket
- Spot: Market data, account, place/cancel orders, trades, transaction history, commission rate, spot–futures transfer
- CLI:
config/list/start/stop/status/test/backup
Installation
pip install -e .
# or
pip install git+https://github.com/asterdex/aster-mcp.git
Quick start
# 1. Configure account (interactive, default HMAC)
aster-mcp config
# V3 key-signing account (EIP-712)
aster-mcp config --account-id main --auth-type v3
# 2. List accounts
aster-mcp list
# 3. Start MCP service (default stdio for Cursor/Claude)
aster-mcp start
# 4. Test connection
aster-mcp test main
Using with Cursor
- Configure at least one account with
aster-mcp config. - Add Aster MCP in Cursor’s MCP settings; command example:
python -m aster_mcp.simple_server(use a Python environment whereaster_mcpis installed).
- Use natural language in chat (e.g. “get Aster BTC price”, “place an Aster order”).
Tool list (summary)
| Category | Futures tools | Spot tools |
|---|---|---|
| Market | get_ticker, get_order_book, get_klines, get_funding_rate, get_funding_info, get_exchange_info, ping |
get_spot_ticker, get_spot_price, get_spot_order_book, get_spot_klines, get_spot_exchange_info |
| Account | get_balance, get_positions, get_account_info, get_account_v4 |
get_spot_account |
| Orders | create_order, cancel_order, cancel_all_orders, get_order, get_open_orders, get_all_orders, get_my_trades |
create_spot_order, cancel_spot_order, cancel_spot_all_orders, get_spot_order, get_spot_open_orders, get_spot_all_orders, get_spot_my_trades |
| Other | set_leverage, set_margin_mode, transfer_funds, get_income, get_commission_rate, get_leverage_bracket |
get_spot_transaction_history, get_spot_commission_rate, transfer_spot_futures |
| System | get_server_info |
Full parameters and integration details: Aster-MCP External Integration Guide.
Project structure
aster-mcp/
├── aster_mcp/
│ ├── __init__.py
│ ├── config.py # Config & encryption
│ ├── client.py # Aster FAPI client (futures, HMAC)
│ ├── v3_client.py # Aster FAPI v3 client (EIP-712)
│ ├── spot_client.py # Aster SAPI client (spot)
│ ├── tools.py # MCP tool implementations
│ ├── simple_server.py
│ └── cli.py
├── docs/
│ └── Aster-MCP-External-Integration.md
├── tests/
├── pyproject.toml
├── requirements.txt
└── README.md
Relation to Aster APIs
- This repo includes Aster FAPI (
client.py, futures) and SAPI (spot_client.py, spot) clients. - Auth:
- HMAC: API Key/Secret for
/fapi/v1,/fapi/v2, etc. - V3 key signing: user (main wallet), signer (API wallet), private_key (signer key), EIP-712; for
/fapi/v3. Requireseth-account.
- HMAC: API Key/Secret for
- Futures base URL:
https://fapi.asterdex.com; Spot base URL:https://sapi.asterdex.com(overridable per account in config). - API docs: aster-finance-futures-api, aster-finance-futures-api-v3, aster-finance-spot-api.
Risk and compliance
- Futures trading involves risk; verify in a test environment first.
- API keys are stored locally with encryption; do not leak or commit them.
- Comply with local regulations and Aster platform terms.
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。