How to integrate Altoviz MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Altoviz logo
OpenAI Agents SDK logo
divider

Introduction

This guide walks you through connecting Altoviz to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Altoviz agent that can find customer details by email address, update a client's company information, retrieve current vat rates for invoices through natural language commands.

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

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

Also integrate Altoviz 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 Altoviz
  • Configure an AI agent that can use Altoviz as a tool
  • Run a live chat session where you can ask the agent to perform Altoviz 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 Altoviz MCP server, and what's possible with it?

The Altoviz MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Altoviz account. It provides structured and secure access to your billing, invoicing, and customer management data, so your agent can manage products, find customers, update records, and retrieve financial information on your behalf.

  • Product management and creation: Instruct your agent to create new products, update details, or delete products from your Altoviz catalog with ease.
  • Customer and contact lookup: Effortlessly find customers or contacts by email, enabling quick access to client details and supporting streamlined communication.
  • Financial classification and VAT management: Let your agent fetch available classifications and VAT rates, ensuring accurate tax handling and financial document setup.
  • Unit retrieval for transactions: Retrieve all available measurement units in your system, supporting precise product and invoice management.
  • Customer information updates: Have your agent modify or update customer records, keeping your business data up-to-date without manual intervention.

Supported Tools & Triggers

Tools
Create ContactCreates a new contact in the Altoviz system.
Create CustomerCreates a new customer in Altoviz.
Create Customer FamilyCreates a new customer family in Altoviz for categorizing and organizing customers into groups.
Create ProductCreates a new product in the Altoviz system.
Create Product FamilyTool to create a new product family in Altoviz.
Create ReceiptCreates a new receipt in the Altoviz system to record customer payments.
Create Sale CreditCreates a new draft credit note (avoir) in Altoviz.
Create Sale InvoiceCreates a new draft sale invoice in Altoviz.
Delete ColleagueTool to delete a colleague from Altoviz.
Delete CustomerTool to delete a customer from Altoviz.
Delete Customer FamilyTool to delete a customer family from Altoviz.
Delete ProductThis tool allows you to delete an existing product from Altoviz.
Delete Product FamilyTool to delete a product family from Altoviz.
Delete ReceiptTool to delete a receipt from Altoviz.
Delete Draft Sale CreditTool to delete a draft credit from Altoviz.
Delete Sale InvoiceTool to delete a draft sale invoice from Altoviz.
Delete Sale QuoteTool to delete a sale quote from Altoviz.
Delete SupplierTool to delete a supplier from Altoviz.
Download Purchase InvoiceTool to download a purchase invoice as a PDF file from Altoviz.
Download Sale Credit PDFTool to download a sale credit as a PDF file from Altoviz.
Download Sale Invoice PDFTool to download a sale invoice as a PDF file from Altoviz.
Find Contact by EmailThis tool allows searching for contacts in Altoviz using an email address.
Find Customer by EmailThis tool allows you to find a customer in Altoviz by their email address.
Find Product by NumberSearch for a product in Altoviz by its product number/SKU.
Find Product by Number or Internal IDTool to find a product in Altoviz by exact product number or internal ID.
Find Receipt by Internal IDTool to find receipts in Altoviz by customer internal ID.
Find Sale CreditsTool to find sale credits in Altoviz.
Find Sale InvoicesTool to find sale invoices in Altoviz.
Find Sale QuotesTool to find sale quotes in Altoviz.
Get Classifications ListThis tool retrieves a list of classifications from the Altoviz platform.
Get Colleague by IDTool to retrieve a colleague's details from Altoviz by their ID.
Get Contact by IDTool to retrieve a contact by its unique ID from Altoviz.
Get Current UserTool to retrieve the current authenticated user's information from Altoviz.
Get Customer by IDTool to retrieve a customer by their ID from Altoviz.
Get Customer by Internal IDTool to retrieve a single customer from Altoviz by their internal ID.
Get Customer ContactsTool to retrieve all contacts associated with a specific customer in Altoviz.
Get Customer FamilyTool to retrieve a customer family by ID from Altoviz.
Get Product by IDTool to retrieve a product by its unique ID in Altoviz.
Get Product Family by IDTool to retrieve a specific product family by its ID from Altoviz.
Get Receipt by IDTool to retrieve a receipt by its ID from Altoviz.
Get Sale Credit by IDTool to retrieve a sale credit by its ID from Altoviz.
Get Sale Invoice by IDTool to retrieve a sale invoice by its ID from Altoviz.
Get SettingsTool to retrieve application settings from Altoviz.
Get Supplier by IDTool to retrieve a supplier by their ID from Altoviz.
Get Supplier ContactsTool to retrieve all contacts associated with a specific supplier in Altoviz.
Get Units ListThis tool retrieves a list of all available units in the Altoviz system.
Get VAT RatesThis tool retrieves a list of all available VAT rates from Altoviz.
List ColleaguesRetrieves a list of colleagues from Altoviz.
List ContactsTool to retrieve a list of contacts from Altoviz with optional filtering and pagination.
List Customer FamiliesTool to list customer families from Altoviz.
List CustomersTool to retrieve a paginated list of customers from Altoviz.
List Product FamiliesTool to retrieve a list of product families from Altoviz.
List ReceiptsTool to retrieve a list of receipts from Altoviz.
List Sale CreditsTool to retrieve a list of sale credits from Altoviz.
List Sale InvoicesTool to retrieve a list of sale invoices from Altoviz.
List Sale QuotesTool to retrieve a list of sale quotes from Altoviz.
List SuppliersTool to retrieve a paginated list of suppliers from Altoviz.
List WebhooksTool to retrieve all configured webhooks from Altoviz.
Register WebhookTool to register a new webhook in Altoviz.
Test API KeyTool to test API key validity and retrieve basic account information.
Unregister WebhookTool to unregister a webhook from Altoviz.
Update Colleague InformationUpdates an existing colleague's information in Altoviz.
Update Customer InformationUpdates an existing customer's information in Altoviz.
Update ReceiptUpdates an existing receipt in Altoviz.
Update Sale CreditTool to update a draft credit note in Altoviz.
Update Supplier InformationUpdates an existing supplier's information in Altoviz.
Upload Purchase InvoiceTool to upload and create a new purchase invoice from a file (PDF or image format).

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 Altoviz 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 Altoviz.

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 Altoviz Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["altoviz"]
)

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 altoviz.
  • The router checks the user's Altoviz connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Altoviz.
  • This approach keeps things lightweight and lets the agent request Altoviz 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 Altoviz. "
        "Help users perform Altoviz 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 Altoviz 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 Altoviz 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 Altoviz.
  • 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 Altoviz 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=["altoviz"]
)
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 Altoviz. "
        "Help users perform Altoviz 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 Altoviz MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Altoviz.

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 Altoviz MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Altoviz MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Altoviz MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Altoviz MCP with Claude Cowork

Codex logo

Codex

Use Altoviz MCP with Codex

OpenClaw logo

OpenClaw

Use Altoviz MCP with OpenClaw

Hermes logo

Hermes

Use Altoviz MCP with Hermes

CLI logo

CLI

Use Altoviz MCP with CLI

Google ADK logo

Google ADK

Use Altoviz MCP with Google ADK

LangChain logo

LangChain

Use Altoviz MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Altoviz MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Altoviz MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Altoviz MCP with LlamaIndex

CrewAI logo

CrewAI

Use Altoviz MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Altoviz MCP?

With a standalone Altoviz MCP server, the agents and LLMs can only access a fixed set of Altoviz tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Altoviz 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 Altoviz tools.

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

Yes, absolutely. You can configure which Altoviz 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 Altoviz 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.

Get started for freeGet a demo↗
Altoviz MCP Integration with OpenAI Agents SDK | Composio