How to integrate Zoho inventory MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable

30 min · no commitment · see it on your stack

Zoho inventory logo
OpenAI Agents SDK logo
divider

Introduction

This guide walks you through connecting Zoho inventory to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Zoho inventory agent that can check current stock for a specific item, list all pending sales orders today, create a new purchase order for supplier through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Zoho inventory account through Composio's Zoho inventory MCP server.

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

Also integrate Zoho inventory with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Zoho inventory
  • Configure an AI agent that can use Zoho inventory as a tool
  • Run a live chat session where you can ask the agent to perform Zoho inventory operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Zoho inventory MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Zoho Inventory account. It provides structured and secure access to your inventory management system, so your agent can perform actions like tracking stock levels, managing sales and purchase orders, updating product details, and syncing inventory across sales channels on your behalf.

  • Real-time stock tracking and updates: Let your agent monitor inventory levels, adjust quantities, and receive alerts when items are running low or out of stock.
  • Order management automation: Have the agent create, update, or track sales and purchase orders, making it easy to keep tabs on every transaction.
  • Product catalog management: Direct your agent to add new products, update existing details, or manage pricing and SKU information to keep your catalog current and accurate.
  • Multi-channel inventory syncing: Enable your agent to synchronize inventory data across multiple online stores and marketplaces, ensuring consistency and reducing errors.
  • Shipment and fulfillment handling: Empower your agent to generate shipment orders, track deliveries, and manage warehouse operations for streamlined fulfillment.

Supported Tools & Triggers

Tools
Add Credit Note CommentTool to add a comment to a credit note in Zoho Inventory.
Add Invoice AttachmentTool to upload an attachment to a specific invoice.
Add Invoice CommentTool to add a comment to a specific invoice in Zoho Inventory.
Apply Credits To InvoicesTool to apply credits from a credit note to one or more invoices.
Bulk Delete Sales OrdersTool to bulk delete sales orders.
Bulk Email InvoicesSends multiple invoices by email to a contact in a single API call.
Bulk Export InvoicesTool to bulk export invoices as a single PDF.
Bulk Print InvoicesGenerate a consolidated PDF containing multiple invoices for printing or archiving.
Bulk Print PackagesTool to bulk print package slips as a consolidated PDF.
Cancel Invoice Write OffTool to cancel write off for an invoice.
Create BillTool to create a bill in Zoho Inventory.
Create ContactTool to create a new contact (customer or vendor) in Zoho Inventory.
Create Contact PersonTool to create a contact person.
Create Credit NoteTool to create a new credit note in Zoho Inventory.
Create Customer PaymentTool to create a customer payment in Zoho Inventory.
Create InvoiceTool to create a new invoice in Zoho Inventory.
Create ItemTool to create a new item in Zoho Inventory.
Create Item GroupTool to create an item group in Zoho Inventory.
Create PackageTool to create a package for a sales order in Zoho Inventory.
Create Purchase OrderTool to create a purchase order in Zoho Inventory.
Create Sales OrderTool to create a sales order in Zoho Inventory.
Deactivate ContactTool to mark a contact as inactive in Zoho Inventory.
Deactivate ItemTool to mark an item as inactive in Zoho Inventory.
Deactivate Item GroupTool to mark an item group as inactive in Zoho Inventory.
Delete Composite ItemPermanently deletes a composite item from Zoho Inventory.
Delete ContactTool to delete a contact.
Delete Contact PersonTool to delete a contact person.
Delete InvoiceTool to delete an invoice.
Delete Invoice AttachmentTool to delete an invoice attachment.
Delete Invoice CommentDelete a specific comment from an invoice in Zoho Inventory.
Delete ItemTool to delete an item.
Delete Item GroupTool to delete an item group.
Delete Item ImageTool to delete an image associated with an item.
Delete PackageTool to delete a package.
Delete Sales OrderTool to delete a sales order.
Disable Payment ReminderTool to disable payment reminders for an invoice.
Email ContactTool to email a contact in Zoho Inventory.
Email Contact StatementTool to email a statement of transactions to a contact.
Email Credit NoteTool to email a credit note to customers.
Email InvoiceTool to email a specific invoice to customers.
Enable Invoice Payment ReminderTool to enable payment reminders for an invoice.
Get ContactTool to retrieve a specific contact by ID from Zoho Inventory.
Get Contact AddressTool to get contact address.
Get Credit NoteTool to retrieve a credit note by ID.
Get Credit Note Email ContentTool to get credit note email content including subject, body, recipients, and available templates.
Get Current UserTool to get details of the currently authenticated user in Zoho Inventory.
Get Sales OrderTool to retrieve the details of an existing sales order.
List BillsTool to list bills.
List ContactsTool to list all contacts (customers and vendors) in Zoho Inventory.
List Credit NotesTool to list all credit notes.
List CurrenciesTool to list all currencies configured in Zoho Inventory.
List Invoice PaymentsTool to list all payments received for a specific invoice.
List InvoicesTool to list all invoices in Zoho Inventory.
List Item GroupsTool to list all item groups in Zoho Inventory.
List ItemsTool to list all items in Zoho Inventory.
List OrganizationsTool to list all organizations the user has access to in Zoho Inventory.
List Purchase OrdersTool to list purchase orders.
List Sales OrdersTool to list sales orders.

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

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Zoho inventory project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Zoho inventory.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Zoho inventory Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["zoho_inventory"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only zoho_inventory.
  • The router checks the user's Zoho inventory connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Zoho inventory.
  • This approach keeps things lightweight and lets the agent request Zoho inventory tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Zoho inventory. "
        "Help users perform Zoho inventory operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Zoho inventory and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Zoho inventory operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Zoho inventory.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Zoho inventory and OpenAI Agents SDK:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["zoho_inventory"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Zoho inventory. "
        "Help users perform Zoho inventory operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Zoho inventory MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Zoho inventory.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Zoho inventory MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Zoho inventory MCP?

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

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Zoho inventory tools.

Can I manage the permissions and scopes for Zoho inventory while using Tool Router?

Yes, absolutely. You can configure which Zoho inventory 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.

How safe is my data with Composio Tool Router?

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 Zoho inventory data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.