What is Payment Mcp Server

The payment-mcp-server is the Paytm Payments MCP Server that allows AI agents and developers to securely access Paytm’s Payments and Business Payments APIs using the Model Context Protocol (MCP). It facilitates smart and contextual automation across various payment workflows.

Use cases

Use cases include automating refunds, tracking settlements, checking transaction statuses, creating payment links, and managing payouts through AI-driven interactions.

How to use

To use the payment-mcp-server, developers need to set up their environment with Python 3.12 or higher and obtain Paytm Merchant credentials (PAYTM_MID and PAYTM_KEY_SECRET). They can then utilize the provided APIs to automate payment operations and interact with payment workflows through natural language prompts.

Key features

Key features include Smart Payment Operations for automating routine tasks, Context-Aware AI Assistants for intelligent transaction management, enhanced Developer Productivity for efficient API calls, and Agentic AI Payments for improved shopping experiences.

Where to use

The payment-mcp-server can be used in e-commerce platforms, financial services, and any application requiring payment processing and automation, particularly where AI-driven solutions are beneficial.

Paytm MCP Server

Paytm MCP Server enables AI agents and developers to securely access Paytm’s Payments and Business Payments APIs via the Model Context Protocol (MCP). It allows smart, contextual automation across all payment workflows

Features

• Smart Payment Ops: Automate routine payment workflows like refunds, settlement tracking, and transaction status checks using AI agents powered by Paytm MCP

• Context-Aware AI Assistants: Create intelligent tools that can fetch and explain transactions, initiate payouts, or manage payment links—all through simple natural language prompts

• Developer Productivity: Supercharge developer efficiency by enabling Paytm API calls (e.g. “Create a ₹500 payment link”) directly via terminals, chat-based UIs, or AI IDE plugins

• Agentic AI Payments: Enable agentic AI payments, build enhanced bot led shopping experience through Paytm MCP server

Tools

Tool	Description	API
create_link	Create a new payment link	Create Link API
fetch_link	Fetch details of a payment link	Fetch Link API
fetch_transaction	Fetch transaction details for a link	Fetch Transaction API
fetch_order_list	Fetch a list of orders within a date range of 30 days	Order List API
initiate_refund	Initiate a refund for a specific transaction	Initiate Refund API
check_refund_status	Check status of a previously initiated refund	Check refund status API
fetch_refund_list	Fetch a list of refunds within a date range of 30 days	Fetch Refund List API

Prerequisites

• Python 3.12 or higher
• Paytm Merchant credentials: PAYTM_MID and PAYTM_KEY_SECRET
• uv (a fast Python package installer and runner)
• Claude Desktop (for running and managing the server)

Installation

Option 1: Automated Setup (Recommended)

1. Download the setup.sh script above for automated installation and configuration and follow the below steps:

2. Run the following in your terminal (Mac/Unix-based):

Make the script executable

# Make the script executable
chmod +x setup.sh

# Run the setup script
./setup.sh

The script will:

1. Check for required dependencies (Python 3.12+, uv, Claude Desktop)
2. Clone or update the repository
3. Create and activate a virtual environment
4. Install all required dependencies
5. Create a .env file template for Paytm credentials

Note: On Windows, use Git Bash or WSL to run the script, or follow manual installation.

Option 2: Manual Installation

1. Clone the repository:

   git clone https://github.com/paytm/payment-mcp-server.git
   cd payment-mcp-server
   

2. Create and activate a virtual environment:

   uv venv
   source .venv/bin/activate
   

3. Install dependencies:

   uv pip install .
   

Running the MCP Server with Claude Desktop

This server is designed to be launched and managed through Claude Desktop. You do not need to run the server manually from the command line.

Sample claude_desktop_config.json

Place this file in your project root or as required by Claude Desktop:

{
  "mcpServers": {
    "paytm-mcp-server": {
      "command": "uv path",
      "args": [
        "--directory",
        "path to project",
        "run",
        "paytm_mcp.py"
      ],
      "env": {
        "PAYTM_MID": "****************",
        "PAYTM_KEY_SECRET": "************"
      }
    }
  }
}

Tips:

1. On Mac:

   • Run which uv to get the command path
   • Run pwd to get the project path

2. On Windows:

   • Run where uv to get the command path
   • Run cd to get the project path

   Ensure the paytm_mcp.py file exists in the given path.

3. The env section should contain your actual Paytm credentials (Paytm MID and Paytm Key Secret)

Next Steps

1. Update the claude_desktop_config.json with your Paytm credentials
2. Restart the server using Claude Desktop
3. Begin interacting with Paytm APIs using your AI agents

License

This project is licensed under the MIT License - see the LICENSE file for details.

The MIT License is a permissive license that allows you to:

• Use the code commercially
• Modify the code
• Distribute the code
• Use the code privately
• Sublicense the code

The only requirement is that the license and copyright notice must be included in all copies or substantial portions of the software.

Need help? Raise an issue or explore the Paytm Documentation