authorize-net-mcp

authorize-net-mcp

Experimental Authorize.net Node.js TypeScript MCP Server

zmarty

Developer Tools
Visit Server

README

authorize-net-mcp

This project is a Model Context Protocol (MCP) server that integrates with the Authorize.net Node SDK to provide two primary payment operations:

  1. takePayment – Immediately charge a credit card (AUTH_CAPTURE).
  2. createInvoice – Generate a hosted payment page (invoice) for customers to pay online.

By exposing these operations as MCP tools, AI agents and other platforms using the MCP Node SDK can seamlessly call Authorize.net functionality without directly handling credit card or transaction logic themselves.

What Is the Model Context Protocol (MCP)?

Model Context Protocol (MCP) is a specification and software development kit (SDK) that standardizes how AI models (e.g., large language models) communicate with external tools and services. MCP servers provide “tools” (methods) that an AI assistant or automation platform can discover and invoke programmatically. The goals of MCP include:

  • Discoverability: Tools advertise their functionality and input/output schemas.
  • Standardized I/O: An AI model or any client can call a tool with a JSON-based schema and receive structured output, making automation workflows more reliable.
  • Security & Compatibility: Tools run in isolated processes and communicate via well-defined channels (e.g., stdio), which helps sandbox them from the AI model environment.

In this project, the takePayment and createInvoice methods are defined as MCP tools with input schemas (amount, card details, invoice info) and structured JSON output. This means any AI model or system that implements the MCP protocol can query this server to learn about available tools, then call them with the correct parameters to process payments via Authorize.net.


How It Works

  1. MCP Node SDK – Provides the framework for creating and running MCP servers in Node.js. We use classes like Server, StdioServerTransport, and schema definitions (ListToolsRequestSchema, CallToolRequestSchema) to register tools and respond to requests over stdio.

  2. Authorize.net Node SDK – Manages the low-level payment transaction calls. Inside our MCP tool handlers, we import the authorizenet package and build requests (e.g., CreateTransactionRequest) with your Authorize.net credentials.

  3. MCP Tools

    • takePayment: Takes a credit card number, expiration date, CVV, and amount, then charges the card immediately.
    • createInvoice: Prepares a transaction with no card data (the card data is collected via a hosted Authorize.net form) and returns a URL to which the customer can be directed to pay the invoice securely.

When the server starts, it advertises these two tools (and their input schemas) to any connected MCP client. The client can then call them as needed.


Project Structure

authorize-net-mcp/
├── package.json
├── tsconfig.json
├── src
│   ├── index.ts               # MCP server initialization
│   ├── models
│   │   └── authorizeNetModel.ts   # JSON schemas & tool specifications
│   └── handlers
│       └── authorizeNetHandlers.ts # Implementations of takePayment & createInvoice
└── README.md
  • src/index.ts: Creates an MCP Server, registers tool handlers, and listens for requests via stdio.
  • src/models/authorizeNetModel.ts: Defines the input/output schemas for the two tools in JSON schema format (advertised to MCP clients when they call ListTools).
  • src/handlers/authorizeNetHandlers.ts: Contains the core logic that integrates with Authorize.net (charging cards, creating hosted invoices).

Getting Started

1. Installation

  1. Clone or download this repository.

  2. Install dependencies:

    npm install
    

2. Set Environment Variables

You must provide your Authorize.net API credentials. For testing, you can use Authorize.net Sandbox credentials. The server will look for:

  • AUTHORIZE_NET_API_LOGIN_ID
  • AUTHORIZE_NET_TRANSACTION_KEY

Set them before you build or start the server:

For Linux/Mac:

export AUTHORIZE_NET_API_LOGIN_ID="YOUR_SANDBOX_LOGIN_ID"
export AUTHORIZE_NET_TRANSACTION_KEY="YOUR_SANDBOX_TRANSACTION_KEY"

For Windows (Command Prompt):

set AUTHORIZE_NET_API_LOGIN_ID=YOUR_SANDBOX_LOGIN_ID
set AUTHORIZE_NET_TRANSACTION_KEY=YOUR_SANDBOX_TRANSACTION_KEY

For Windows (PowerShell):

$env:AUTHORIZE_NET_API_LOGIN_ID="YOUR_SANDBOX_LOGIN_ID"
$env:AUTHORIZE_NET_TRANSACTION_KEY="YOUR_SANDBOX_TRANSACTION_KEY"

3. Build and Run

# Build the TypeScript
npm run build

# Start the MCP server (listening on stdio)
npm start

The server will run and wait for MCP requests. Typically, an AI assistant or automation tool that understands MCP will spawn or connect to this process and invoke the takePayment or createInvoice tools by name.


Using the MCP Tools

Within an MCP-compatible environment (e.g., an AI chat that supports MCP), the workflow might be:

  1. List available tools (the server returns [takePayment, createInvoice] plus their schemas).

  2. Call the takePayment tool with arguments:

    {
      "amount": 19.99,
      "cardNumber": "4242424242424242",
      "expirationDate": "0825",
      "cardCode": "123"
    }
    
    • The server returns whether the payment was successful and includes transaction details in the response message.
  3. Call the createInvoice tool with arguments:

    {
      "amount": 50.0,
      "invoiceNumber": "INV-1001",
      "description": "T-shirt order"
    }
    
    • The server responds with a URL for the hosted payment page. Direct the customer to that link to enter card details securely.

Notes on Production Usage

  • Security: Never commit real API keys to source control. Use environment variables or secret management solutions in production.
  • HTTPS: In a real deployment, ensure you’re using HTTPS endpoints or secure tunnels for any inbound requests, if you plan to call it outside of an MCP host.
  • Sandbox vs. Production: Switch the base URL in the authorizeNetHandlers.ts file to production endpoints once you’re ready to go live.

Further Reading


License

This project is released under the MIT License (or your preferred license). Please see the repository’s LICENSE file for details.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
MCP Package Docs Server

MCP Package Docs Server

Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.

Featured
Local
TypeScript
Claude Code MCP

Claude Code MCP

An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.

Featured
Local
JavaScript
@kazuph/mcp-taskmanager

@kazuph/mcp-taskmanager

Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.

Featured
Local
JavaScript
Linear MCP Server

Linear MCP Server

Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.

Featured
JavaScript
mermaid-mcp-server

mermaid-mcp-server

A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.

Featured
JavaScript
Jira-Context-MCP

Jira-Context-MCP

MCP server to provide Jira Tickets information to AI coding agents like Cursor

Featured
TypeScript
Linear MCP Server

Linear MCP Server

A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Featured
JavaScript
Sequential Thinking MCP Server

Sequential Thinking MCP Server

This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Featured
Python