PayFast MCP Server
Enables AI assistants to interact with the PayFast payment gateway to manage transactions, subscriptions, and refunds. It provides a suite of 13 tools with built-in human-in-the-loop safety confirmations for high-risk financial operations.
README
payfast-mcp
A Model Context Protocol (MCP) server for PayFast, South Africa's leading payment gateway. Enables AI assistants like Claude to securely interact with your PayFast merchant account.
Features
- Transaction management — fetch transaction details, query history, process tokenized charges
- Subscription management — fetch, pause, unpause, cancel, update, and ad-hoc charge subscriptions
- Refund processing — create refunds (full or partial) and query refund status
- Credit card queries — look up credit card transaction details
- Sandbox support — defaults to sandbox mode for safe testing
- Secure by design — credentials via environment variables only, sensitive data never logged
Available Tools
| Tool | Description | Risk |
|---|---|---|
ping |
Test API connectivity | Low |
transaction_fetch |
Get transaction by ID | Low |
transaction_history |
Query transaction history | Low |
transaction_charge |
Charge a stored token | Medium |
subscription_fetch |
Get subscription details | Low |
subscription_pause |
Pause a subscription | High |
subscription_unpause |
Resume a subscription | Medium |
subscription_cancel |
Cancel a subscription | High |
subscription_update |
Update subscription terms | High |
subscription_adhoc |
Ad-hoc subscription charge | High |
refund_create |
Process a refund | High |
refund_fetch |
Get refund details | Low |
creditcard_fetch |
Query card transaction | Low |
High-risk operations require human approval before execution.
Quick Start
Prerequisites
- Node.js 18+
- A PayFast merchant account (sandbox or production)
Installation
npm install -g payfast-mcp
Or run directly with npx:
npx payfast-mcp
Configuration
Set the following environment variables:
| Variable | Required | Description |
|---|---|---|
PAYFAST_MERCHANT_ID |
Yes | Your PayFast Merchant ID |
PAYFAST_MERCHANT_KEY |
Yes | Your PayFast Merchant Key |
PAYFAST_PASSPHRASE |
Yes | Your PayFast API Passphrase |
PAYFAST_ENVIRONMENT |
No | sandbox (default) or production |
You can also create a .env file in your working directory.
Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"payfast": {
"command": "npx",
"args": ["-y", "payfast-mcp"],
"env": {
"PAYFAST_MERCHANT_ID": "your-merchant-id",
"PAYFAST_MERCHANT_KEY": "your-merchant-key",
"PAYFAST_PASSPHRASE": "your-passphrase",
"PAYFAST_ENVIRONMENT": "sandbox"
}
}
}
}
Claude Code
Add to your Claude Code settings:
claude mcp add payfast \
-e PAYFAST_MERCHANT_ID=your-merchant-id \
-e PAYFAST_MERCHANT_KEY=your-merchant-key \
-e PAYFAST_PASSPHRASE=your-passphrase \
-e PAYFAST_ENVIRONMENT=sandbox \
-- npx -y payfast-mcp
Cursor
Add to your Cursor MCP config (.cursor/mcp.json for project-level, or ~/.cursor/mcp.json for global):
{
"mcpServers": {
"payfast": {
"command": "npx",
"args": ["-y", "payfast-mcp"],
"env": {
"PAYFAST_MERCHANT_ID": "your-merchant-id",
"PAYFAST_MERCHANT_KEY": "your-merchant-key",
"PAYFAST_PASSPHRASE": "your-passphrase",
"PAYFAST_ENVIRONMENT": "sandbox"
}
}
}
}
Codex
Add via the Codex CLI:
codex mcp add payfast \
--env PAYFAST_MERCHANT_ID=your-merchant-id \
--env PAYFAST_MERCHANT_KEY=your-merchant-key \
--env PAYFAST_PASSPHRASE=your-passphrase \
--env PAYFAST_ENVIRONMENT=sandbox \
-- npx -y payfast-mcp
Or add directly to ~/.codex/config.toml:
[mcp_servers.payfast]
command = "npx"
args = ["-y", "payfast-mcp"]
[mcp_servers.payfast.env]
PAYFAST_MERCHANT_ID = "your-merchant-id"
PAYFAST_MERCHANT_KEY = "your-merchant-key"
PAYFAST_PASSPHRASE = "your-passphrase"
PAYFAST_ENVIRONMENT = "sandbox"
Development
# Clone the repo
git clone https://github.com/jpbester/payfast-mcp.git
cd payfast-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# Run with MCP Inspector
npm run inspect
License
MIT
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。