How to integrate Quaderno MCP with Autogen

Framework Integration Gradient
Quaderno Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Quaderno to AutoGen using the Composio tool router. By the end, you'll have a working Quaderno agent that can calculate tax rate for a u.s. sale, create an invoice for a new customer, email finalized invoice to a client, add a new product with custom tax through natural language commands.

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

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

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 Quaderno
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Quaderno tools
  • Run a live chat loop where you ask the agent to perform Quaderno 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 Quaderno MCP server, and what's possible with it?

The Quaderno MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Quaderno account. It provides structured and secure access to your tax automation, invoicing, and compliance workflows, so your agent can calculate taxes, generate invoices, manage contacts and products, and handle essential document delivery on your behalf.

  • Automated tax rate calculation: Ask your agent to instantly determine the correct tax rate for any address or transaction type before creating invoices or processing sales.
  • Invoice creation and delivery: Let your agent generate detailed invoices for customers and deliver them directly via email, ensuring seamless billing operations.
  • Contact and product management: Easily create new customer or vendor contacts, add new products, or permanently delete outdated items from your Quaderno account—all through your agent.
  • Expense and tax ID cleanup: Direct your agent to remove specific expenses or registered tax IDs when they're no longer needed, keeping your records tidy and up to date.
  • Credit note and coupon handling: Your agent can deliver finalized credit notes to customers and permanently delete coupons as part of your accounting and revenue operations.

Supported Tools & Triggers

Tools
Calculate Tax RateTool to calculate applicable tax rate for given address and transaction type.
Create ContactTool to create a new contact (customer or vendor).
Create InvoiceTool to create a new invoice.
Create ProductTool to create a new product.
Delete CouponTool to permanently delete a coupon.
Delete ExpenseTool to permanently delete an expense by id.
Delete ProductTool to permanently delete a product by id.
Delete Tax IDTool to permanently delete a registered tax id by id.
Deliver Credit NoteTool to deliver a credit note to the customer via email.
Deliver InvoiceTool to deliver an invoice to the customer via email.
List ContactsTool to list contacts, paginated and filterable by name, email, or tax id.
List CouponsTool to list all coupons.
List EvidenceTool to list all evidence objects.
List ExpensesTool to list all expenses, paginated.
List Tax JurisdictionsTool to list all tax jurisdictions.
List ProductsTool to list all products.
List Registered Tax IDsTool to list all registered tax ids.
List Reporting RequestsTool to list all reporting requests.
List SessionsTool to list all quaderno checkout sessions, paginated and filterable by status.
List Tax CodesTool to list all supported tax codes.
List WebhooksTool to list all webhooks.
Retrieve ContactTool to retrieve details of an existing contact by id.
Retrieve CouponTool to retrieve details of an existing coupon by id.
Retrieve EvidenceTool to retrieve details of an existing evidence object by id.
Retrieve InvoiceTool to retrieve details of an existing invoice by id.
Retrieve Tax JurisdictionTool to retrieve a tax jurisdiction by id.
Retrieve ProductTool to retrieve details of an existing product by id.
Update Credit NoteTool to update a credit note.
Update InvoiceTool to update an invoice.
Update productTool to update a product; unspecified fields remain unchanged.
Validate Tax IDTool to validate a tax id.
Void Credit NoteTool to void a credit note.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

You will need:

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

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.

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 Quaderno via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Quaderno connections to use

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 Quaderno session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["quaderno"]
    )
    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 Quaderno tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Quaderno assistant agent with MCP tools
    agent = AssistantAgent(
        name="quaderno_assistant",
        description="An AI assistant that helps with Quaderno 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 Quaderno tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Quaderno 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 Quaderno 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 Quaderno 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 Quaderno session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["quaderno"]
    )
    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 Quaderno assistant agent with MCP tools
        agent = AssistantAgent(
            name="quaderno_assistant",
            description="An AI assistant that helps with Quaderno 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 Quaderno 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 Quaderno 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 Quaderno, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Quaderno MCP Agent with another framework

FAQ

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

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

Can I use Tool Router MCP with Autogen?

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 Quaderno tools.

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

Yes, absolutely. You can configure which Quaderno 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 Quaderno data and credentials are handled as safely as possible.

Used by agents from

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