Alpaca Trading Bot MCP Server
Exposes Alpaca paper trading as MCP tools for checking quotes, managing a watchlist, checking market hours, and placing simulated trades.
README
Alpaca Trading Bot (MCP Server)
An MCP server exposing Alpaca paper trading as tools for Claude (or any MCP client): check quotes, manage a watchlist, check market hours, and place simulated trades. No real money is ever at risk — paper=True is hardcoded in trading_mcp_server.py.
Setup
python -m venv .venv
.venv/Scripts/activate # or source .venv/bin/activate on macOS/Linux
pip install -r requirements.txt
cp .env.example .env # then fill in your Alpaca paper trading keys
Get paper trading API keys from the Alpaca dashboard (alpaca.markets) — sign up, then generate a key under the Paper Trading section (not Live).
Running
python trading_mcp_server.py
This runs as a stdio MCP server. To register it with Claude Code:
claude mcp add alpaca-trading -- python /full/path/to/trading_mcp_server.py
Tools
get_account— cash, buying power, portfolio valueget_quotes(symbols?)— latest bid/ask for given tickers, or the whole watchlist if omittedget_watchlist/add_to_watchlist(symbol)/remove_from_watchlist(symbol)— managewatchlist.jsonis_market_open— checks Alpaca's trading calendar (accounts for weekends + market holidays)list_positions— current open positionsplace_order(symbol, qty, side)— market order, paper trading onlylist_orders— recent order history
Watchlist
watchlist.json seeds the top 25 QQQM (Nasdaq-100) holdings by weight, verified via stockanalysis.com. Edit the file directly, or use the add_to_watchlist / remove_from_watchlist tools.
Not yet built
- Scheduled runs (e.g. every 30 minutes during market hours): the MCP server itself only responds to on-demand tool calls — it does not self-schedule. Options discussed but not decided: a local script + Task Scheduler/cron, or an Azure Function with a timer trigger (Azure Functions has GA support for MCP tool triggers as of Build 2026 — see
functions-bindings-mcp-tool-triggerdocs).is_market_openis the building block for whichever scheduler wraps it. - Autonomous vs. approval-gated trading: not yet decided whether the AI should place orders on its own or require confirmation each time.
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。