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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.