Square logo

Square

Organization
square

A Model Context Protocol (MCP) server for square

Publishersquare
Repositorysquare-mcp-server
LanguageTypeScript
Forks
22
Stars
99
Available tools
0
Transport typestreamable-http
Categories
LicenseApache-2.0
Links
  • Connect tools to AI workflows

    Square exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    99 stars and 22 forks from the linked repository.

Square Model Context Protocol Server (Beta)

This project follows the Model Context Protocol standard, allowing AI assistants to interact with Square's connect API.

Quick Start

Get up and running with the Square MCP server using npx:

bash
# Basic startup
npx square-mcp-server start

# With environment configuration
ACCESS_TOKEN=YOUR_SQUARE_ACCESS_TOKEN SANDBOX=true npx square-mcp-server start

# local runs
npx /path/to/project/square-mcp-server

Replace YOUR_SQUARE_ACCESS_TOKEN with your actual Square access token. You can obtain your access token by following the guide at Square Access Tokens. You can also set environment variables before running the command.

Remote MCP Server

Square now offers a hosted remote MCP server at:

https://mcp.squareup.com/sse

The remote MCP is recommended as it uses OAuth authentication, allowing you to log in with your Square account directly without having to create or manage access tokens manually.

Configuration Options

Environment VariablePurposeExample
ACCESS_TOKENYour Square API access tokenACCESS_TOKEN=sq0atp-...
SANDBOXUse Square sandbox environmentSANDBOX=true
PRODUCTIONUse Square production environmentPRODUCTION=true
DISALLOW_WRITESRestrict to read-only operationsDISALLOW_WRITES=true
SQUARE_VERSIONSpecify Square API versionSQUARE_VERSION=2025-04-16

Integration with AI Assistants

Goose Integration

To configure the Square MCP Server with Goose:

Remote MCP

To install the Square remote MCP in Goose, click this URL on a computer where Goose is installed:

goose://extension?cmd=npx&arg=mcp-remote&arg=https%3A%2F%2Fmcp.squareup.com%2Fsse&id=square_mcp_production_remote&name=Square%20MCP%20Remote&description=Square%20Production%20MCP%20Remote

Or copy and paste the URL into your browser's address bar.

bash
# Automatic installation
npx square-mcp-server install

# Get URL for manual installation
npx square-mcp-server get-goose-url

The install command automatically updates your Goose configuration.

Claude Desktop Integration

For Claude Desktop integration, see the Model Context Protocol Quickstart Guide. Add this configuration to your claude_desktop_config.json:

Remote MCP

json
{
  "mcpServers": {
    "mcp_square_api": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.squareup.com/sse"]
    }
  }
}

This approach allows you to authenticate directly with your Square account credentials without needing to manage access tokens.

Local MCP

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

Tool Reference

The Square MCP Server provides a streamlined set of tools for interacting with Square APIs:

ToolDescriptionPrimary Use
get_service_infoDiscover methods available for a serviceExploration and discovery
get_type_infoGet detailed parameter requirementsRequest preparation
make_api_requestExecute API calls to SquarePerforming operations

Service Catalog

Square MCP Server provides access to Square's complete API ecosystem. Check out the Square API Documentation for detailed information about each service:

ServiceDescription
applepayApple Pay integration
bankaccountsBank account management
bookingcustomattributesCustom attributes for bookings
bookingsAppointment booking management
cardsPayment card management
cashdrawersCash drawer management
catalogCatalog management (items, categories, etc.)
checkoutCheckout and payment processing
customercustomattributesCustom attributes for customers
customergroupsCustomer grouping
customersegmentsCustomer segmentation
customersCustomer management
devicesSquare device management
disputesPayment dispute handling
eventsEvent tracking
giftcardactivitiesGift card activity tracking
giftcardsGift card management
inventoryInventory tracking
invoicesInvoice management
laborWorkforce management
locationcustomattributesCustom attributes for locations
locationsLocation management
loyaltyLoyalty program management
merchantcustomattributesCustom attributes for merchants
merchantsMerchant account management
oauthAuthentication
ordercustomattributesCustom attributes for orders
ordersOrder management
paymentsPayment processing
payoutsPayout management
refundsRefund management
sitesWebsite integration
snippetsSquare Online Code integration
subscriptionsSubscription management
teamStaff management
terminalSquare Terminal management
vendorsSupplier management
webhooksubscriptionsEvent notifications

Usage Pattern

For optimal interaction with the Square API through MCP:

  1. Discover: Use get_service_info to explore available methods

    get_service_info(service: "catalog")
  2. Understand: Use get_type_info to learn parameter requirements

    get_type_info(service: "catalog", method: "list")
  3. Execute: Use make_api_request to perform the operation

    make_api_request(service: "catalog", method: "list", request: {})

Development and Debugging

Using MCP Inspector

The MCP Inspector provides a visual interface for testing:

bash
# Build the project
npm run build

# Start the inspector with the Square MCP Server
npx @modelcontextprotocol/inspector node dist/index.js start

Development Workflow

  1. Clone the repository
  2. Install dependencies: npm install
  3. Start development mode: npm run watch
  4. Run the server: node dist/index.js start
  5. Test your changes using the MCP Inspector

Contributing

This repository is auto-generated from Square's OpenAPI Specification. While contributions are welcome, please note that changes will need to be incorporated into the generator that produces this code. Please open an issue to discuss proposed changes before submitting a pull request.

Installation

TypingMind
{
  "mcpServers": {
    "mcp_square_api": {
      "url": "https://mcp.squareup.com/sse"
    }
  }
}

Use Square MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Square is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP connects through a hosted MCP server URL in TypingMind.

Add an MCP server URL

Use this when Square is already hosted remotely or your team wants one shared connector that multiple users can access.

1

Open MCP connectors

In TypingMind, go to Plugins, open MCP connectors, then choose Add URL.

  1. Open TypingMind in your browser.
  2. Go to Plugins.
  3. Open MCP connectors.
  4. Click Add URL.
TypingMind Add Custom MCP Server URL form
2

Paste the server URL

Enter https://mcp.squareup.com/sse in the Server URL field. Add a connection name, description, icon, custom HTTP headers, or OAuth client settings if the server requires them.

  1. Paste https://mcp.squareup.com/sse into the Server URL field.
  2. Enter a connection name for Square.
  3. Add a description and icon if you want it to be easier to identify.
  4. Add custom HTTP headers or OAuth client details if the server requires authentication.
3

Create the connection

Click Create connection, then return to the Plugins list and confirm the new MCP connection is active.

  1. Click Create connection.
  2. Return to the MCP connectors list.
  3. Confirm the Square connection appears as active.
  4. Refresh the plugin list if the connection does not appear immediately.
4

Switch models without reconnecting

Start a chat with your preferred model, enable the Square tools from Plugins, and switch to another model whenever needed. The MCP connection stays available to the TypingMind workspace.

  1. Start a new chat in TypingMind.
  2. Select the AI model you want to use.
  3. Enable the Square tools from Plugins.
  4. Ask the model to use the tool when needed.
  5. Switch to another AI model and reuse the same MCP connection.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Square to help me with this task?
Square
Sure. I read it.
Here is what I found using Square.

Frequently asked questions

What is the Square MCP server used for?

Square is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Square MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Square with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Square MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Square connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Square MCP to TypingMind?

Square can be connected in TypingMind by adding its hosted MCP server URL. This is useful when you want a remote MCP connection that is available from your TypingMind workspace.

What tools does Square MCP provide in TypingMind?

Square exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Square MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Square requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇