Integrate AI with Your Square Account: Using the Square Model Context Protocol Server

Want to connect your AI assistant to your Square account? The Square Model Context Protocol (MCP) Server allows AI assistants to interact directly with Square's powerful Connect API. This article breaks down how to get started, configure your server, and use it effectively.

What is the Square Model Context Protocol Server?

The Square MCP Server acts as a bridge between AI tools and your Square account. Using the Model Context Protocol standard, it allows you to leverage AI for tasks like:

• Managing your product catalog.
• Processing payments.
• Retrieving customer data.

This unlocks new possibilities for automation and intelligent insights within your Square ecosystem.

Quick Start: Launching Your Square MCP Server

Here's how to quickly launch the Square MCP Server and get it running:

• Basic Startup: npx square-mcp-server start
• With Environment Configuration (Recommended): ACCESS_TOKEN=YOUR_SQUARE_ACCESS_TOKEN SANDBOX=true npx square-mcp-server start
• Local Runs: npx /path/to/project/square-mcp-server

Important: Replace YOUR_SQUARE_ACCESS_TOKEN with your actual Square access token. You can find instructions on how to obtain your access token on the Square developer website. Setting SANDBOX=true is recommended.

Configuring for AI Assistants: Goose and Claude

The Square MCP Server integrates seamlessly with popular AI assistants. Here's how to set it up:

Goose Integration

• Automatic Installation: npx square-mcp-server install
• Get URL for Manual Installation: npx square-mcp-server get-goose-url

The install command handles most of the configuration automatically, making it incredibly simple.

Claude Desktop Integration

For Claude Desktop users, add this configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "mcp_square_api": {
      "command": " npx ",
      "args": [
        " square-mcp-server ",
        " start "
      ],
      "env": {
        "ACCESS_TOKEN": " YOUR_SQUARE_ACCESS_TOKEN ",
        "SANDBOX": " true "
      }
    }
  }
}

Mastering the Usage Pattern

To effectively interact with the Square API through the Model Context Protocol server, follow this pattern:

1. Discover: Find available requests using get_service_info(service: "catalog").
2. Understand: Determine the needed parameters by using get_type_info(service: "catalog", method: "list").
3. Execute: Perform the operation by executing make_api_request(service: "catalog", method: "list", request: {}).

This structured approach empowers you to control the Square API via AI, leading to efficient workflows.

Development and Debugging: Using the MCP Inspector

The MCP Inspector offers a visual interface to test and debug your Square Model Context Protocol (MCP) integrations.

1. Build the project: npm run build
2. Start the inspector: npx @modelcontextprotocol/inspector node dist/index.js start

This allows you to visually inspect the requests and responses, ensuring everything is functioning correctly. This is especially helpful when first learning to connect AI to your Square account.

Contributing to the Project

The Square Model Context Protocol server is continuously evolving. Share your ideas! Since it's auto-generated from Square's OpenAPI Specification, open an issue to discuss any changes before submitting a pull request.

By following these steps, you can harness the power of AI to streamline your Square operations with the Square Model Context Protocol (MCP) server.