Alpaca MCP Server
This is a Model Context Protocol (MCP) server implementation for Alpaca's Trading API. It enables large language models (LLMs) on Claude Desktop, Cursor, or VScode to interact with Alpaca's trading infrastructure using natural language (English). This server supports stock trading, options trading, portfolio management, watchlist handling, and real-time market data access.
Features
- Market Data
- Real-time quotes, trades, and price bars for stocks
- Historical price data and trading history
- Option contract quotes and Greeks (via snapshots)
- Account Management
- View balances, buying power, and account status
- Inspect all open and closed positions
- Position Management
- Get detailed info on individual holdings
- Liquidate all or partial positions by share count or percentage
- Order Management
- Place stock and option orders (market or limit)
- Cancel orders individually or in bulk
- Retrieve full order history
- Options Trading
- Search and view option contracts by expiration or strike price
- Place multi-leg options strategies
- Get latest quotes and Greeks for contracts
- Market Status & Corporate Actions
- Check if markets are open
- Fetch market calendar and trading sessions
- View upcoming corporate announcements (earnings, splits, dividends)
- Watchlist Management
- Create, update, and view personal watchlists
- Manage multiple watchlists for tracking assets
- Asset Search
- Query details for stocks and other Alpaca-supported assets
0. Prerequisites
- Python
- GitHub account
- Alpaca API keys (with paper or live trading access)
- Claude for Desktop or another compatible MCP client
1. Installation
-
Clone the repository and navigate to the directory:
git clone https://github.com/alpacahq/alpaca-mcp-server.git cd alpaca-mcp-server -
Create and activate a virtual environment:
python3 -m venv venv source venv/bin/activateNote: The virtual environment will use the Python version that was used to create it. If you run the command with Python 3.10 or newer, your virtual environment will also use Python 3.10+. If you want to confirm the version, you can run
python3 --versionafter activating the virtual environment. -
Install the required packages:
pip install -r requirements.txt
Project Structure
After cloning and activating the virtual environment, your directory structure should look like this:
alpaca-mcp-server/ ← This is the workspace folder (= project root)
├── alpaca_mcp_server.py ← Script is directly in workspace root
├── .github/ ← VS Code settings (for VS Code users)
│ ├── core/ ← Core utility modules
│ └── workflows/ ← GitHub Actions workflows
├── .vscode/ ← VS Code settings (for VS Code users)
│ └── mcp.json
├── venv/ ← Virtual environment folder
│ └── bin/python
├── .env.example ← Environment template (use this to create `.env` file)
├── .gitignore
├── Dockerfile ← Docker configuration (for Docker use)
├── .dockerignore ← Docker ignore (for Docker use)
├── requirements.txt
└── README.md
2. Create and edit a .env file for your credentials in the project directory
-
Copy the example environment file in the project root by running this command:
cp .env.example .env -
Replace the credentials (e.g. API keys) in the
.envfile:ALPACA_API_KEY = "your_alpaca_api_key_for_paper_account" ALPACA_SECRET_KEY = "your_alpaca_secret_key_for_paper_account" ALPACA_PAPER_TRADE = True TRADE_API_URL = None TRDE_API_WSS = None DATA_API_URL = None STREAM_DATA_WSS = None
Claude Desktop Usage
To use Alpaca MCP Server with Claude Desktop, please follow the steps below. The official Claude Desktop setup document is available here: https://modelcontextprotocol.io/quickstart/user
Start the MCP Server
Open a terminal in the project root directory and run the following command (or use python -m alpaca_mcp_server):
python alpaca_mcp_server.py
Claude for Desktop Configuration
- Open Claude Desktop
- Navigate to:
Settings → Developer → Edit Config - Update your
claude_desktop_config.json:
Note:
Replace <project_root> with the path to your cloned alpaca-mcp-server directory. This should point to the Python executable inside the virtual environment you created with python3 -m venv venv in the terminal.
{
"mcpServers": {
"alpaca": {
"command": "<project_root>/venv/bin/python",
"args": [
"/path/to/alpaca-mcp-server/alpaca_mcp_server.py"
],
"env": {
"ALPACA_API_KEY": "your_alpaca_api_key_for_paper_account",
"ALPACA_SECRET_KEY": "your_alpaca_secret_key_for_paper_account"
}
}
}
}
Claude Code Usage
To use Alpaca MCP Server with Claude Code, please follow the steps below.
The claude mcp add command is part of Claude Code. If you have the Claude MCP CLI tool installed (e.g. by npm install -g @anthropic-ai/claude-code), you can use this command to add the server to Claude Code:
claude mcp add alpaca \
/path/to/your/alpaca-mcp-server/venv/bin/python \
/path/to/your/alpaca-mcp-server/alpaca_mcp_server.py \
-e ALPACA_API_KEY=your_api_key \
-e ALPACA_SECRET_KEY=your_secret_key
Note: Replace the paths with your actual project directory paths. This command automatically adds the MCP server configuration to Claude Code without manual JSON editing.
The Claude MCP CLI tool needs to be installed separately. Check following the official pages for availability and installation instructions
- Learn how to set up MCP with Claude Code
- Install, authenticate, and start using Claude Code on your development machine
Cursor Usage
To use Alpaca MCP Server with Cursor, please follow the steps below. The official Cursor MCP setup document is available here: https://docs.cursor.com/context/mcp
Prerequisites
- Cursor IDE installed with Claude AI enabled
- Python and virtual environment set up (follow Installation steps above)
Configure the MCP Server
Method 1: Using JSON Configuration
Create or edit ~/.cursor/mcp.json (macOS/Linux) or %USERPROFILE%\.cursor\mcp.json (Windows):
{
"mcpServers": {
"alpaca": {
"command": "/path/to/your/alpaca-mcp-server/venv/bin/python",
"args": [
"/path/to/your/alpaca-mcp-server/alpaca_mcp_server.py"
],
"env": {
"ALPACA_API_KEY": "your_alpaca_api_key",
"ALPACA_SECRET_KEY": "your_alpaca_secret_key"
}
}
}
}
Method 2: Using Cursor Settings UI
- Open Cursor Settings → Tools & Integrations → MCP Tools
- Click "+ New MCP Server"
- Configure with the same details as the JSON method above
Note: Replace the paths with your actual project directory paths and API credentials.
VS Code Usage
To use Alpaca MCP Server with VS Code, please follow the steps below.
VS Code supports MCP servers through GitHub Copilot's agent mode. The official VS Code setup document is available here: https://code.visualstudio.com/docs/copilot/chat/mcp-servers
Prerequisites
- VS Code with GitHub Copilot extension installed and active subscription
- Python and virtual environment set up (follow Installation steps above)
- MCP support enabled in VS Code (see below)
1. Enable MCP Support in VS Code
- Open VS Code Settings (Ctrl/Cmd + ,)
- Search for "chat.mcp.enabled" to check the box to enable MCP support
- Search for "github.copilot.chat.experimental.mcp" to check the box to use instruction files
2. Configure the MCP Server
Recommendation: Use workspace-specific configuration (.vscode/mcp.json) instead of user-wide configuration. This allows different projects to use different API keys (multiple paper accounts or live trading) and keeps trading tools isolated from other development work.
For workspace-specific settings:
-
Create
.vscode/mcp.jsonin your project root. -
Add the Alpaca MCP server configuration manually to the mcp.json file:
For Linux/macOS:
{ "mcp": { "servers": { "alpaca": { "type": "stdio", "command": "bash", "args": ["-c", "cd ${workspaceFolder} && source ./venv/bin/activate && python alpaca_mcp_server.py"], "env": { "ALPACA_API_KEY": "your_alpaca_api_key", "ALPACA_SECRET_KEY": "your_alpaca_secret_key" } } } } }For Windows:
{ "mcp": { "servers": { "alpaca": { "type": "stdio", "command": "cmd", "args": ["/c", "cd /d ${workspaceFolder} && .\\venv\\Scripts\\activate && python alpaca_mcp_server.py"], "env": { "ALPACA_API_KEY": "your_alpaca_api_key", "ALPACA_SECRET_KEY": "your_alpaca_secret_key" } } } } }Note: Replace
${workspaceFolder}with your actual project path. For example:- Linux/macOS:
/Users/username/Documents/alpaca-mcp-server - Windows:
C:\\Users\\username\\Documents\\alpaca-mcp-server
- Linux/macOS:
For user-wide settings:
To configure an MCP server for all your workspaces, you can add the server configuration to your user settings.json file. This allows you to reuse the same server configuration across multiple projects.
Specify the server in the mcp VS Code user settings (settings.json) to enable the MCP server across all workspaces.
{
"mcp": {
"servers": {
"alpaca": {
"type": "stdio",
"command": "bash",
"args": ["-c", "cd ${workspaceFolder} && source ./venv/bin/activate && python alpaca_mcp_server.py"],
"env": {
"ALPACA_API_KEY": "your_alpaca_api_key",
"ALPACA_SECRET_KEY": "your_alpaca_secret_key"
}
}
}
}
}
PyCharm Usage
To use the Alpaca MCP Server with PyCharm, please follow the steps below. The official setup guide for configuring the MCP Server in PyCharm is available here: https://www.jetbrains.com/help/ai-assistant/configure-an-mcp-server.html
PyCharm supports MCP servers through its integrated MCP client functionality. This configuration ensures proper logging behavior and prevents common startup issues.
-
Open PyCharm Settings
- Go to
File → Settings - Navigate to
Tools → Model Context Protocol (MCP)(or similar location depending on PyCharm version)
- Go to
-
Add New MCP Server
- Click
Addor+to create a new server configuration. You can also import the settings from Claude by clicking the corresponding button. - Name: Enter any name you prefer for this server configuration (e.g., Alpaca MCP).
- Command: "/path/to/your/alpaca-mcp-server/venv/bin/python"
- Arguments: "alpaca_mcp_server.py"
- Working directory: "/path/to/your/alpaca-mcp-server"
- Click
-
Set Environment Variables Add the following environment variables in the Environment Variables parameter:
ALPACA_API_KEY="your_alpaca_api_key" ALPACA_SECRET_KEY="your_alpaca_secret_key" MCP_CLIENT=pycharm
Docker Usage
To use Alpaca MCP Server with Docker, please follow the steps below.
Prerequisite:
You must have Docker installed on your system.
Run the latest published image (recommended for most users)
docker run -it --rm \
-e ALPACA_API_KEY=your_alpaca_api_key \
-e ALPACA_SECRET_KEY=your_alpaca_secret_key \
ghcr.io/chand1012/alpaca-mcp-server:latest
This pulls and runs the latest published version of the server. Replace your_alpaca_api_key and your_alpaca_secret_key with your actual keys. If the server exposes a port (e.g., 8080), add -p 8080:8080 to the command.
Build and run locally (for development or custom changes)
docker build -t alpaca-mcp-server .
docker run -it --rm \
-e ALPACA_API_KEY=your_alpaca_api_key \
-e ALPACA_SECRET_KEY=your_alpaca_secret_key \
alpaca-mcp-server
Use this if you want to run a modified or development version of the server.
Using with Claude Desktop
{
"mcpServers": {
"alpaca": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e", "ALPACA_API_KEY",
"-e", "ALPACA_SECRET_KEY",
"ghcr.io/chand1012/alpaca-mcp-server:latest"
],
"env": {
"ALPACA_API_KEY": "your_alpaca_api_key",
"ALPACA_SECRET_KEY": "your_alpaca_secret_key"
}
}
}
}
Environment variables can be set either with -e flags or in the "env" object, but not both. For Claude Desktop, use the "env" object.
Security Note: Never share your API keys or commit them to public repositories. Be cautious when passing secrets as environment variables, especially in shared or production environments.
For more advanced Docker usage: See the official Docker documentation.
🔐 API Key Configuration for Live Trading
This MCP server connects to Alpaca's paper trading API by default for safe testing. To enable live trading with real funds, update the following configuration files:
Set Your API Credentials in Two Places:
-
Update environment file in the project directory
Provide your live account keys as environment variables in the
.envfile:ALPACA_API_KEY = "your_alpaca_api_key_for_live_account" ALPACA_SECRET_KEY = "your_alpaca_secret_key_for_live_account" ALPACA_PAPER_TRADE = False TRADE_API_URL = None TRADE_API_WSS = None DATA_API_URL = None STREAM_DATA_WSS = None -
Update Configuration file
For example, when using Claude Desktop, provide your live account keys as environment variables in
claude_desktop_config.json:{ "mcpServers": { "alpaca": { "command": "<project_root>/venv/bin/python", "args": [ "/path/to/alpaca_mcp_server.py" ], "env": { "ALPACA_API_KEY": "your_alpaca_api_key_for_live_account", "ALPACA_SECRET_KEY": "your_alpaca_secret_key_for_live_account" } } } }
Available Tools
Account & Positions
get_account_info()– View balance, margin, and account statusget_positions()– List all held assetsget_open_position(symbol)– Detailed info on a specific positionclose_position(symbol, qty|percentage)– Close part or all of a positionclose_all_positions(cancel_orders)– Liquidate entire portfolio
Stock Market Data
get_stock_quote(symbol)– Real-time bid/ask quoteget_stock_bars(symbol, days=5, timeframe="1Day", limit=None, start=None, end=None)– OHLCV historical bars with flexible timeframes (1Min, 5Min, 1Hour, 1Day, etc.)get_stock_latest_trade(symbol, feed=None, currency=None)– Latest market trade priceget_stock_latest_bar(symbol, feed=None, currency=None)– Most recent OHLC barget_stock_snapshot(symbol_or_symbols, feed=None, currency=None)– Comprehensive snapshot with latest quote, trade, minute bar, daily bar, and previous daily barget_stock_trades(symbol, days=5, limit=None, sort=Sort.ASC, feed=None, currency=None, asof=None)– Trade-level history
Orders
get_orders(status, limit)– Retrieve all or filtered ordersplace_stock_order(symbol, side, quantity, order_type="market", limit_price=None, stop_price=None, trail_price=None, trail_percent=None, time_in_force="day", extended_hours=False, client_order_id=None)– Place a stock order of any type (market, limit, stop, stop_limit, trailing_stop)cancel_order_by_id(order_id)– Cancel a specific ordercancel_all_orders()– Cancel all open orders
Options
get_option_contracts(underlying_symbol, expiration_date=None, expiration_month=None, expiration_year=None, expiration_week_start=None, strike_price_gte=None, strike_price_lte=None, type=None, status=None, root_symbol=None, limit=None)– Fetch contracts with comprehensive filtering optionsget_option_latest_quote(option_symbol)– Latest bid/ask on contractget_option_snapshot(symbol_or_symbols)– Get Greeks and underlyingplace_option_market_order(legs, order_class=None, quantity=1, time_in_force=TimeInForce.DAY, extended_hours=False)– Execute option strategy
Market Info & Corporate Actions
get_market_clock()– Market open/close scheduleget_market_calendar(start, end)– Holidays and trading daysget_corporate_announcements(...)– Earnings, dividends, splits
Watchlists
create_watchlist(name, symbols)– Create a new listupdate_watchlist(watchlist_id, name=None, symbols=None)– Modify an existing listget_watchlists()– Retrieve all saved watchlists
Assets
get_asset_info(symbol)– Search asset metadataget_all_assets(status=None, asset_class=None, exchange=None, attributes=None)– List all tradable instruments with filtering options
Example Natural Language Queries
See the "Example Queries" section below for 50 real examples covering everything from trading to corporate data to option strategies.
Basic Trading
- What's my current account balance and buying power on Alpaca?
- Show me my current positions in my Alpaca account.
- Buy 5 shares of AAPL at market price.
- Sell 5 shares of TSLA with a limit price of $300.
- Cancel all open stock orders.
- Cancel the order with ID abc123.
- Liquidate my entire position in GOOGL.
- Close 10% of my position in NVDA.
- How many shares of AMZN do I currently hold?
- Place a limit order to buy 100 shares of MSFT at $450.
- Place a market order to sell 25 shares of META.
Option Trading
- Show me available option contracts for AAPL expiring next month.
- Get the latest quote for the AAPL250613C00200000 option.
- Retrieve the option snapshot for the SPY250627P00400000 option.
- Liquidate my position in 2 contracts of QQQ calls expiring next week.
- Place a market order to buy 1 call option on AAPL expiring next Friday.
- What are the option Greeks for the TSLA250620P00500000 option?
- Find TSLA option contracts with strike prices within 5% of the current market price.
- Get SPY call options expiring the week of June 16th, 2025, within 10% of market price.
- Place a bull call spread using AAPL June 6th options: one with a 190.00 strike and the other with a 200.00 strike.
Market Information
- Is the US stock market currently open?
- What are the market open and close times today?
- Show me the market calendar for next week.
- Are there any corporate announcements for major tech stocks this month?
- What are the next dividend announcements for SPY?
Historical & Real-time Data
- Show me AAPL's daily price history for the last 5 trading days.
- What was the closing price of TSLA yesterday?
- Get the latest bar for GOOGL.
- What was the latest trade price for NVDA?
- Show me the most recent quote for MSFT.
- Retrieve the last 100 trades for AMD.
- Show me 1-minute bars for AMZN from the last 2 hours.
- Get 5-minute intraday bars for TSLA from last Tuesday through last Friday.
- Get a comprehensive stock snapshot for AAPL showing latest quote, trade, minute bar, daily bar, and previous daily bar all in one view.
- Compare market snapshots for TSLA, NVDA, and MSFT to analyze their current bid/ask spreads, latest trade prices, and daily performance.
Orders
- Show me all my open and filled orders from this week.
- What orders do I have for AAPL?
- List all limit orders I placed in the past 3 days.
- Filter all orders by status: filled.
- Get me the order history for yesterday.
Watchlists
- Create a new watchlist called "Tech Stocks" with AAPL, MSFT, and NVDA.
- Update my "Tech Stocks" watchlist to include TSLA and AMZN.
- What stocks are in my "Dividend Picks" watchlist?
- Remove META from my "Growth Portfolio" watchlist.
- List all my existing watchlists.
Asset Information
- Search for details about the asset 'AAPL'.
- Show me the top 5 tradable crypto assets by trading volume.
- Filter assets with status 'active' for tech stocks.
Combined Scenarios
- Get today's market clock and show me my buying power before placing a limit buy order for TSLA at $340.
- Place a bull call spread with SPY July 3rd options: buy one 5% above and sell one 3% below the current SPY price.
Example Outputs
The MCP server provides detailed, well-formatted responses for various trading queries. Here are some examples:
Option Greeks Analysis
Query: "What are the option Greeks for TSLA250620P00500000?"
Response: Option Details:
- Current Bid/Ask: $142.62 / $143.89
- Last Trade: $138.85
- Implied Volatility: 92.54%
Greeks:
- Delta: -0.8968 (Very Bearish)
- Gamma: 0.0021 (Low Rate of Change)
- Theta: -0.2658 (Time Decay: $26.58/day)
- Vega: 0.1654 (Volatility Sensitivity)
- Rho: -0.3060 (Interest Rate Sensitivity)
Key Insights:
- High Implied Volatility (92.54%)
- Deep In-the-Money (Delta: -0.90)
- Significant Time Decay ($27/day)
Multi-Leg Option Order
Query: "Place a bull call spread using AAPL June 6th options: one with a 190.00 strike and the other with a 200.00 strike."
Response: Order Details:
- Order ID: fc1c04b1-8afa-4b2d-aab1-49613bbed7cb
- Order Class: Multi-Leg (MLEG)
- Status: Pending New
- Quantity: 1 spread
Spread Legs:
-
Long Leg (BUY):
- AAPL250606C00190000 ($190.00 strike)
- Status: Pending New
-
Short Leg (SELL):
- AAPL250606C00200000 ($200.00 strike)
- Status: Pending New
Strategy Summary:
- Max Profit: $10.00 per spread
- Max Loss: Net debit paid
- Breakeven: $190 + net debit paid
These examples demonstrate the server's ability to provide:
- Detailed market data analysis
- Comprehensive order execution details
- Clear strategy explanations
- Well-formatted, easy-to-read responses
The server maintains this level of detail and formatting across all supported queries, making it easy to understand and act on the information provided.
Security Notice
This server can place real trades and access your portfolio. Treat your API keys as sensitive credentials. Review all actions proposed by the LLM carefully, especially for complex options strategies or multi-leg trades.
Usage Analytics Notice
The user agent for API calls defaults to 'ALPACA-MCP-SERVER' to help Alpaca identify MCP server usage and improve user experience. You can opt out by modifying the 'USER_AGENT' constant in '.github/core/user_agent_mixin.py' or by removing the 'UserAgentMixin' from the client class definitions in 'alpaca_mcp_server.py' — though we kindly hope you'll keep it enabled to support ongoing improvements.
License
MIT