How to integrate Razorpay MCP with Autogen

This guide walks you through connecting Razorpay to AutoGen using the Composio tool router. By the end, you'll have a working Razorpay agent that can list recent razorpay payment failures, create payment link for invoice, fetch refund status for customer through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Razorpay account through Composio's Razorpay MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Razorpay logoRazorpay
Api KeyOauth2

Razorpay is a payment gateway and financial services platform for Indian businesses. It helps companies accept payments, manage refunds, send invoices, and run payouts.

42 Tools

Introduction

This guide walks you through connecting Razorpay to AutoGen using the Composio tool router. By the end, you'll have a working Razorpay agent that can list recent razorpay payment failures, create payment link for invoice, fetch refund status for customer through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Razorpay account through Composio's Razorpay MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Razorpay with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Razorpay
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Razorpay tools
  • Run a live chat loop where you ask the agent to perform Razorpay operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Razorpay MCP server, and what's possible with it?

The Razorpay MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Razorpay account. It provides structured and secure access to your payments, orders, customers, invoices, payment links, settlements, and disputes, so your agent can collect payments, manage billing, review transactions, reconcile settlements, and monitor disputes on your behalf.

  • Payment collection and tracking: Have your agent create orders and payment links, review incoming payments, and cancel payment links that are no longer needed.
  • Customer and payment method management: Let the agent create customers, retrieve customer records, and review their saved payment methods.
  • Invoice and item management: Direct your agent to create billing items and invoices, update draft invoices, issue them to customers, and resend invoice notifications by email or SMS.
  • Transaction and settlement review: Instruct your agent to review orders, payments, and invoices, or retrieve settlement reconciliation reports for a specific date or month.
  • Dispute monitoring: Have your agent list payment disputes so your team can review and follow up on contested transactions.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Razorpay account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Razorpay via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Razorpay connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Razorpay session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["razorpay"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Razorpay tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Razorpay assistant agent with MCP tools
    agent = AssistantAgent(
        name="razorpay_assistant",
        description="An AI assistant that helps with Razorpay operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Razorpay tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Razorpay related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Razorpay tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Razorpay and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Razorpay session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["razorpay"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Razorpay assistant agent with MCP tools
        agent = AssistantAgent(
            name="razorpay_assistant",
            description="An AI assistant that helps with Razorpay operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Razorpay related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Razorpay through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Razorpay, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Razorpay action and event your agent gets out of the box.

Cancel Invoice

Tool to cancel an existing Razorpay invoice.

Cancel Payment Link

Tool to cancel a specific payment link.

Create an Order

Tool to create a Razorpay order with specified amount and currency.

Create Contact

Tool to create a contact for payouts in RazorpayX.

Create Customer

Tool to create a new customer in Razorpay.

Create an Invoice

Tool to create an invoice for billing customers.

Create Item

Tool to create an item that can be used in Razorpay invoices.

Create Payment Link

Tool to create a payment link for collecting payments via a shareable URL.

Delete Invoice

Tool to delete an invoice in Razorpay.

Delete item

Tool to delete an existing item from Razorpay.

Fetch All Customers

Tool to retrieve a paginated list of all customers from Razorpay.

Fetch All Invoices

Tool to fetch all invoices with pagination and filtering support.

Fetch All Payment Links

Tool to fetch all payment links with pagination and filtering support.

Fetch All Payments

Tool to retrieve all payments from your Razorpay account with pagination and time filtering support.

Fetch all refunds for a payment

Tool to retrieve all refunds for a specific payment using the Razorpay API.

Fetch a Payment Link

Tool to retrieve details of a specific payment link by its ID.

Fetch Invoice by ID

Tool to fetch a specific invoice by its ID from Razorpay.

Fetch All Orders

Tool to retrieve a paginated list of all orders from Razorpay.

Fetch Order by ID

Tool to fetch details of a specific Razorpay order using its order ID.

Fetch payments by order

Tool to fetch all payments made for a particular order.

Fetch All Refunds

Tool to retrieve all refunds created by you using the Razorpay API.

Get Contact

Tool to retrieve details of a specific contact by ID in RazorpayX.

Retrieve Customer

Tool to retrieve details of a specific customer by their ID.

Get Fund Account

Tool to retrieve details of a specific fund account by its ID.

Get Item

Tool to retrieve complete details of a specific Razorpay item by its ID.

Get Settlement Reconciliation Report

Tool to fetch settlement reconciliation report for a specific date or month from Razorpay.

Get Transfer Reversals

Tool to fetch all reversals for a specific transfer using the Razorpay Route API.

Issue an Invoice

Tool to issue a draft Razorpay invoice to send it to the customer.

List Customer Tokens

Tool to retrieve all tokens (saved payment methods) for a customer.

List Disputes

Tool to retrieve a list of all disputes with pagination support.

List Fund Accounts

Tool to retrieve a list of all fund accounts from RazorpayX with pagination support.

List Fund Validations

Tool to fetch all fund account validation transactions from RazorpayX with pagination support.

List Items

Tool to retrieve a list of all items from Razorpay with pagination support.

List Payment Downtimes

Tool to fetch all active payment method downtimes from Razorpay.

Notify Payment Link

Tool to send or resend notification for a payment link via SMS or email.

Send/Resend Invoice Notification

Tool to send or resend an invoice notification via email or SMS.

Update Contact

Tool to update an existing contact's details in RazorpayX.

Update Customer

Tool to update an existing customer's details in Razorpay.

Update Invoice

Tool to update an existing draft invoice in Razorpay.

Update Item

Tool to update an existing item's details in Razorpay.

Update Order

Tool to update an existing order in Razorpay.

Update payment link

Tool to update an existing payment link in Razorpay.

FAQ

Frequently asked questions

With a standalone Razorpay MCP server, the agents and LLMs can only access a fixed set of Razorpay tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Razorpay and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Autogen fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Razorpay tools.

Yes, absolutely. You can configure which Razorpay scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Razorpay data and credentials are handled as safely as possible.

Start with Razorpay.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Razorpay tool your agent needs.Free to start.

Start building