What are the runtime requirements?
Python 3.10 or higher, along with the packages `mcp`, `alpaca-py`, and `python-dotenv`. You also need a valid Alpaca API key and secret key.
@idsts2670
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp_server_Alpaca_Trading_API": {
"command": "python",
"args": [
"alpaca_mcp_server.py"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
The Alpaca MCP Server is a Model Context Protocol server that allows LLMs like Claude to interact with the Alpaca trading API. It enables trading stocks, checking positions, fetching market data, and managing your account through natural language.
Install Python 3.10+, clone the repository, install required packages (mcp, alpaca-py, python-dotenv), and create a .env file with your Alpaca API credentials. Run the server with python alpaca_mcp_server.py, then configure Claude for Desktop by adding the server to claude_desktop_config.json with the appropriate path and environment variables.
Python 3.10 or higher, along with the packages `mcp`, `alpaca-py`, and `python-dotenv`. You also need a valid Alpaca API key and secret key.
It uses API key authentication. You provide your Alpaca API key ID and secret key (via `.env` file or environment variables in the config). By default, the server uses Alpaca's paper trading environment.
Yes. You can change from paper trading to real money trading by modifying the `TradingClient` initialization parameter `paper=True` to `paper=False` in the server code.
All account and order data is stored on Alpaca's servers. The server only retrieves or sends data through their API; it does not store any data locally.
This server will have access to your Alpaca account and can place real trades. Always review what Claude is suggesting before approving any trades.

Agent-Native Terminal

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links
Mobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.
评论