Alpaca MCP Server Integration

What does “Alpaca” MCP Server do?

The Alpaca MCP (Model Context Protocol) Server is a specialized integration layer that allows AI assistants and large language models (LLMs) to interact with Alpaca’s trading platform using natural language commands. By connecting through MCP, developers and users can trade stocks and options, analyze financial data, manage portfolios, handle watchlists, and access real-time market information directly from their favorite LLM tools and IDEs such as Claude Desktop, Cursor, and VScode. This server bridges the gap between AI agents and trading infrastructure, making tasks like placing orders, retrieving historical data, or monitoring asset watchlists seamless and accessible through conversational interfaces, thereby streamlining the workflow for algorithmic trading, financial analysis, and portfolio management.

List of Prompts

No prompt templates are explicitly mentioned in the provided repository or documentation.

List of Resources

No explicit MCP resources are described in the provided files or documentation.

List of Tools

No explicit list of tools is included in the accessible files or documentation.

Use Cases of this MCP Server

• Stock and Options Trading
  Use natural language to place, modify, and cancel stock and options trades directly from an LLM-powered interface, enabling algorithmic and discretionary trading workflows without manual platform navigation.

• Portfolio Management
  View account balances, inspect open and closed positions, and manage your holdings using conversational commands to streamline portfolio oversight and rebalancing.

• Market Data Retrieval
  Request real-time and historical market data, including quotes, trades, price bars, and option Greeks, to support research and strategy development.

• Watchlist Management
  Create and manage personalized watchlists for tracking assets, helping users monitor multiple securities and react to market changes efficiently.

• Order History and Market Status
  Retrieve full order history, check the market’s open/close status, and access corporate action data (earnings, splits, dividends) for comprehensive account and market awareness.

How to set it up

Windsurf

No Windsurf-specific instructions are provided in the available documentation or code.

Claude

1. Prerequisites:

   • Install Python 3.10+
   • Clone the repository and install dependencies
   • Obtain Alpaca API keys

2. Create/Edit .env file:
   Add the following to your .env in the project directory:

   ALPACA_API_KEY = "your_alpaca_api_key"
   ALPACA_SECRET_KEY = "your_alpaca_secret_key"
   PAPER = True
   

3. Start MCP Server:

   python alpaca_mcp_server.py
   

4. Configure Claude Desktop:

   • Open Claude Desktop
   • Navigate to: Settings → Developer → Edit Config
   • Update your claude_desktop_config.json:

     {
       "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",
             "ALPACA_SECRET_KEY": "your_alpaca_secret_key"
           }
         }
       }
     }
     

5. Save configuration and restart Claude Desktop

Cursor

No Cursor-specific instructions are provided in the available documentation or code.

Cline

No Cline-specific instructions are provided in the available documentation or code.

Securing API Keys

API keys are specified using environment variables, as shown in the env section of the JSON configuration:

"env": {
  "ALPACA_API_KEY": "your_alpaca_api_key",
  "ALPACA_SECRET_KEY": "your_alpaca_secret_key"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "MCP-name": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “MCP-name” to whatever the actual name of your MCP server is (e.g., “alpaca”, “github-mcp”, etc.) and replace the URL with your own MCP server URL.

Overview

Between these two tables, the Alpaca MCP server offers strong documentation on setup and core use cases, but lacks explicit details on MCP prompt templates, exposed tools, and resource definitions. It’s well-suited for trading and market data workflows, but would benefit from more detailed MCP-specific documentation. Rating: 6/10.

MCP Score