
Square Model Context Protocol Server
Enables AI assistants to interact with Square's Connect API through the Model Context Protocol standard, allowing for operations like managing customers, processing payments, and handling inventory.
Tools
make_api_request
Unified tool for all Square API operations. Be sure to get types before calling. Available services: applepay, bankaccounts, bookingcustomattributes, bookings, cards, cashdrawers, catalog, checkout, customercustomattributes, customergroups, customersegments, customers, devices, disputes, events, giftcardactivities, giftcards, inventory, invoices, labor, locationcustomattributes, locations, loyalty, merchantcustomattributes, merchants, oauth, ordercustomattributes, orders, payments, payouts, refunds, sites, snippets, subscriptions, team, terminal, vendors, webhooksubscriptions.
get_type_info
Get type information for a Square API method. You must call this before calling the make_api_request tool.
get_service_info
Get information about a Square API service. Call me before trying to get type info
README
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:
# 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.
Configuration Options
Environment Variable | Purpose | Example |
---|---|---|
ACCESS_TOKEN |
Your Square API access token | ACCESS_TOKEN=sq0atp-... |
SANDBOX |
Use Square sandbox environment | SANDBOX=true |
PRODUCTION |
Use Square production environment | PRODUCTION=true |
DISALLOW_WRITES |
Restrict to read-only operations | DISALLOW_WRITES=true |
SQUARE_VERSION |
Specify Square API version | SQUARE_VERSION=2025-04-16 |
Integration with AI Assistants
Goose Integration
To configure the Square MCP Server with Goose:
# 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
:
{
"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:
Tool | Description | Primary Use |
---|---|---|
get_service_info |
Discover methods available for a service | Exploration and discovery |
get_type_info |
Get detailed parameter requirements | Request preparation |
make_api_request |
Execute API calls to Square | Performing 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:
Service | Description |
---|---|
applepay |
Apple Pay integration |
bankaccounts |
Bank account management |
bookingcustomattributes |
Custom attributes for bookings |
bookings |
Appointment booking management |
cards |
Payment card management |
cashdrawers |
Cash drawer management |
catalog |
Catalog management (items, categories, etc.) |
checkout |
Checkout and payment processing |
customercustomattributes |
Custom attributes for customers |
customergroups |
Customer grouping |
customersegments |
Customer segmentation |
customers |
Customer management |
devices |
Square device management |
disputes |
Payment dispute handling |
events |
Event tracking |
giftcardactivities |
Gift card activity tracking |
giftcards |
Gift card management |
inventory |
Inventory tracking |
invoices |
Invoice management |
labor |
Workforce management |
locationcustomattributes |
Custom attributes for locations |
locations |
Location management |
loyalty |
Loyalty program management |
merchantcustomattributes |
Custom attributes for merchants |
merchants |
Merchant account management |
oauth |
Authentication |
ordercustomattributes |
Custom attributes for orders |
orders |
Order management |
payments |
Payment processing |
payouts |
Payout management |
refunds |
Refund management |
sites |
Website integration |
snippets |
Square Online Code integration |
subscriptions |
Subscription management |
team |
Staff management |
terminal |
Square Terminal management |
vendors |
Supplier management |
webhooksubscriptions |
Event notifications |
Usage Pattern
For optimal interaction with the Square API through MCP:
-
Discover: Use
get_service_info
to explore available methodsget_service_info(service: "catalog")
-
Understand: Use
get_type_info
to learn parameter requirementsget_type_info(service: "catalog", method: "list")
-
Execute: Use
make_api_request
to perform the operationmake_api_request(service: "catalog", method: "list", request: {})
Development and Debugging
Using MCP Inspector
The MCP Inspector provides a visual interface for testing:
# Build the project
npm run build
# Start the inspector with the Square MCP Server
npx @modelcontextprotocol/inspector node dist/index.js start
Development Workflow
- Clone the repository
- Install dependencies:
npm install
- Start development mode:
npm run watch
- Run the server:
node dist/index.js start
- 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.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。