Alpaca MCP Server
@tedlikeskix
About Alpaca MCP Server
Model Context Protocol (MCP) server for Alpaca trading API
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"alpaca-mcp-server": {
"command": "python",
"args": [
"alpaca_mcp_server.py"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Alpaca MCP Server?
Alpaca MCP Server is a Model Context Protocol (MCP) server that enables LLMs like Claude to interact with the Alpaca trading API through natural language. It allows trading stocks, checking positions, fetching market data, and managing account information.
How to use Alpaca MCP Server?
Install Python 3.10+, Alpaca API keys, and an MCP client. Clone the repository, install required packages (mcp, alpaca-py, python-dotenv), create a .env file with your API credentials, and run python alpaca_mcp_server.py. Configure Claude for Desktop by adding the server to claude_desktop_config.json with the API keys.
Key features of Alpaca MCP Server
- Real‑time stock quotes and historical price bars
- Account balances, buying power, and status checks
- View current portfolio positions and performance
- Place market and limit orders via natural language
- List, track, and cancel open orders
Use cases of Alpaca MCP Server
- Check your current account balance and buying power
- View all open positions in your portfolio
- Get the latest stock quote or historical price data
- Place a market or limit order through conversation
- Cancel all open orders or close all positions
FAQ from Alpaca MCP Server
What API credentials are required?
You need an Alpaca API key ID and secret key, which can be set in a .env file or directly in the claude_desktop_config.json environment variables.
Can I use real money trading?
The server uses Alpaca's paper trading by default. To switch to real money trading, change paper=True to paper=False inside the TradingClient initialization.
Which MCP clients are supported?
The README explicitly shows configuration for Claude for Desktop, but the server should work with any MCP client.
How do I run the server?
After installing dependencies and setting up credentials, run python alpaca_mcp_server.py from the project directory.
Are there any security considerations?
Yes, the MCP server has access to your Alpaca account and can place real trades. Always review suggestions before approving any trades.
Frequently asked questions
What API credentials are required?
You need an Alpaca API key ID and secret key, which can be set in a `.env` file or directly in the `claude_desktop_config.json` environment variables.
Can I use real money trading?
The server uses Alpaca's paper trading by default. To switch to real money trading, change `paper=True` to `paper=False` inside the `TradingClient` initialization.
Which MCP clients are supported?
The README explicitly shows configuration for Claude for Desktop, but the server should work with any MCP client.
How do I run the server?
After installing dependencies and setting up credentials, run `python alpaca_mcp_server.py` from the project directory.
Are there any security considerations?
Yes, the MCP server has access to your Alpaca account and can place real trades. Always review suggestions before approving any trades.
Basic information
More Other MCP servers
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
🪟 Windows-MCP
CursorTouchMCP Server for Computer Use in Windows
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Unity MCP ✨
justinpbarnettUnity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Website
FunnyWolfAdversary simulation and Red teaming platform with AI
Comments