Global Payments MCP Server
Enables AI agents to create and manage payment links programmatically via the Global Payments API, supporting single-use and multi-use links, retrieval, and API documentation retrieval.
README
Global Payments MCP Server (TypeScript)
A Model Context Protocol (MCP) server for Global Payments API integration, enabling AI agents to create and manage payment links programmatically using TypeScript/Node.js.
Table of Contents
About
This MCP server bridges AI agents (like Claude or GitHub Copilot) with the Global Payments API, allowing natural language payment link creation, retrieval, and management with automatic authentication, token management, and comprehensive error handling. Built with TypeScript for type safety and modern Node.js development.
Features
- Payment link creation (single-use and multi-use)
- Payment link retrieval and filtering
- API documentation retrieval (19+ API categories)
Prerequisites
-
Node.js 18.0 or higher
-
npm
-
Global Payments API credentials (Get them here)
-
Claude Desktop, VS Code with Copilot, or another MCP-compatible client
Note: It is recommended that the app being used has limited access. specifically only the LNK related resources should be added in the App permissions
Installation
-
Clone the repository
git clone https://github.com/globalpayments/mcp-server.git cd gpapi-mcp-server/Typescript -
Install dependencies
npm install -
Build the project
npm run build -
Create
.envfile in the project rootCreate a
.envfile in the TypeScript directory with your credentials:# Required: Your Global Payments App credentials (format: APP_ID:APP_SECRET) GPAPI_APP=your_app_id:your_app_secret # Optional: Your Global Payments Account (provide ONE of these, or leave blank for auto-detection) # If not provided, the account will be auto-detected from the access token # GPAPI_ACCOUNT_ID=your_account_id # OR # GPAPI_ACCOUNT_NAME=your_account_name # Optional: Environment (SANDBOX, or PROD, default: SANDBOX) ENV=SANDBOXNote: The
.envfile is the recommended way to store credentials. It keeps sensitive information out of your configuration files and makes it easier to manage different environments. -
Configure Your MCP Client
For Claude Desktop
Add to your
claude_desktop_config.json:{ "mcpServers": { "global-payments": { "command": "node", "args": [ "X://absolute//path//to//gpapi-mcp-server//Typescript//lib//index.js" ], "env":{ "GPAPI_APP":"XXXXXXXXXXXXXXXXX:XXXXXXX", "GPAPI_ACCOUNT_NAME":"XXXXXXXXX", "ENV":"SANDBOX" } } } }For VS Code (Copilot)
Add to your VS Code MCP settings file (
mcp.json):{ "servers": { "global-payments": { "command": "node", "args": [ "lib/index.js" ], "cwd": "./", "env":{ "GPAPI_APP":"XXXXXXXXXXXXXXXXX:XXXXXXX", "GPAPI_ACCOUNT_NAME":"XXXXXXXXX", "ENV":"SANDBOX" } } } }Note: Ensure you provide the absolute path to your TypeScript project directory in the
cwdfield. The.envfile should be located in this directory.
Available Tools
This MCP server provides the following tools:
| Tool | Description |
|---|---|
create_payment_link |
Create single-use or multi-use payment links |
get_links |
Retrieve and filter payment links |
get_documentation |
Retrieve API documentation for 19+ categories |
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。