Razorpay MCP Server

Razorpay MCP Server

Unofficial Razorpay MCP server

LightHeads

Developer Tools
Visit Server

README

Razorpay MCP Server

Connect your Razorpay payment gateway to AI assistants using the Model Context Protocol

A Model Context Protocol (MCP) server for interacting with the Razorpay payment gateway API. This package enables AI assistants like Cursor, Claude, and Copilot to directly access your Razorpay account data through a standardized interface.

Quick Start

The most reliable way to use this package:

# Install globally first
npm install -g razorpay-mcp@0.1.4

# Then use the binary directly
razorpay-mcp-stdio --key-id rzp_test_yourkeyid --key-secret yoursecretkey

Cursor Configuration

After installing globally, add this configuration to your .cursor/mcp.json file:

{
  "mcpServers": {
    "razorpay": {
      "command": "razorpay-mcp-stdio",
      "args": [
        "--key-id",
        "rzp_test_yourkeyid",
        "--key-secret",
        "yoursecretkey"
      ]
    }
  }
}

For Windows Users

{
  "mcpServers": {
    "razorpay": {
      "command": "cmd",
      "args": [
        "/c",
        "razorpay-mcp-stdio",
        "--key-id",
        "rzp_test_yourkeyid",
        "--key-secret",
        "yoursecretkey"
      ]
    }
  }
}

For Web Applications (Using SSE)

  1. Start the SSE server:
# Install globally first
npm install -g razorpay-mcp@0.1.4

# Then use the binary directly
razorpay-mcp-sse --key-id rzp_test_yourkeyid --key-secret yoursecretkey --port 3001
  1. Connect from your web app:
// Create SSE connection
const eventSource = new EventSource('http://localhost:3001/sse');

// Handle connection event
eventSource.onmessage = (event) => {
  const data = JSON.parse(event.data);
  
  // If this is a hello message, store the sessionId
  if (data.type === 'hello') {
    const sessionId = data.sessionId;
    console.log(`Connected with session ID: ${sessionId}`);
    
    // Now you can make API calls
    callRazorpayAPI(sessionId, 'getAllPayments', {count: 10});
  }
};

// Send API requests
async function callRazorpayAPI(sessionId, toolName, params) {
  const response = await fetch(`http://localhost:3001/messages?sessionId=${sessionId}`, {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      type: 'toolCall',
      id: Date.now().toString(),
      name: toolName,
      params
    })
  });
  return response.json();
}

Docker Usage

You can also run this MCP server using Docker:

Build the Docker Image

# Clone the repository
git clone https://github.com/yourusername/razorpay-mcp.git
cd razorpay-mcp

# Build the Docker image
docker build -t razorpay-mcp .

Run the Container

For the stdio transport (for direct use with Cursor):

docker run --rm -it razorpay-mcp node dist/transports/stdio.cjs \
  --key-id rzp_test_yourkeyid --key-secret yoursecretkey

For the SSE server (for web applications):

docker run --rm -p 3001:3001 razorpay-mcp node dist/transports/sse.cjs \
  --key-id rzp_test_yourkeyid --key-secret yoursecretkey --port 3001

Available Razorpay Tools

Tool Name Description Parameters
getAllPayments Fetch payments with pagination count, skip, from, to
getAllOrders Fetch orders with pagination count, skip, from, to
getAllSettlements Fetch settlements with pagination count, skip, from, to
getAllRefunds Fetch refunds with pagination count, skip, from, to
getAllDisputes Fetch disputes with pagination count, skip, from, to
getAllInvoices Fetch invoices with pagination count, skip, from, to
getAllContacts Fetch contacts with pagination count, skip, from, to
getAllTransactions Fetch transactions with pagination count, skip, from, to
getAllVPAs Fetch Virtual Payment Addresses count, skip, from, to
getAllCustomers Fetch customers with pagination count, skip, from, to
getAccountBalance Fetch account balance accountId

All pagination parameters are optional:

  • count: Number of items to fetch (default: 10, max: 100)
  • skip: Number of items to skip
  • from: Start timestamp
  • to: End timestamp

Resources

License

Apache-2.0

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