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 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.