How to integrate Booqable MCP with Autogen

This guide walks you through connecting Booqable to AutoGen using the Composio tool router. By the end, you'll have a working Booqable agent that can add a new customer named alice brown, list all active orders for this week, create a rental order for customer id 123 through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Booqable account through Composio's Booqable MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Booqable logoBooqable
Api Key

Booqable is a rental software platform for managing inventory, bookings, and reservations. It helps businesses streamline rentals and keep track of every item with ease.

49 Tools

Introduction

This guide walks you through connecting Booqable to AutoGen using the Composio tool router. By the end, you'll have a working Booqable agent that can add a new customer named alice brown, list all active orders for this week, create a rental order for customer id 123 through natural language commands.

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

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

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

The Booqable MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Booqable account. It provides structured and secure access to your rental management system, so your agent can perform actions like creating customers, managing orders, retrieving inventory data, and organizing product groups on your behalf.

  • Customer management and onboarding: Effortlessly create new customers, fetch details for existing clients, or delete customer records when needed—all through your AI agent.
  • Order creation and tracking: Let your agent generate new rental orders, retrieve specific order details, or list and filter all existing orders based on your business needs.
  • Inventory and product group organization: Have your agent create new product groups to organize inventory, fetch product group information, or remove groups that are no longer needed.
  • Automated cleanup and archiving: Direct your agent to archive customers or orders, helping you keep your database clean and up-to-date without manual intervention.

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 Booqable 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 Booqable 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 Booqable 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 Booqable session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["booqable"]
    )
    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 Booqable 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 Booqable assistant agent with MCP tools
    agent = AssistantAgent(
        name="booqable_assistant",
        description="An AI assistant that helps with Booqable 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 Booqable 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 Booqable 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 Booqable 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 Booqable 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 Booqable session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["booqable"]
    )
    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 Booqable assistant agent with MCP tools
        agent = AssistantAgent(
            name="booqable_assistant",
            description="An AI assistant that helps with Booqable 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 Booqable 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 Booqable 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 Booqable, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Create Customer

Tool to create a new customer.

Create Order

Tool to create a new order.

Create Product Group

Tool to create a new product group in Booqable.

Delete Customer

Tool to delete (archive) a customer by ID.

Delete Order

Tool to delete (archive) an order by ID.

Delete Product Group

Tool to delete a product group by ID.

Get Customer

Tool to fetch a specific customer by ID.

Get Customers

Tool to retrieve a list of customers.

Get Inventory Levels

Tool to fetch inventory levels for products.

Get New Order

Tool to retrieve a new order template with default values.

Get Order

Tool to retrieve a specific order by ID.

Get Product

Tool to fetch a specific product by ID.

Get Product Group

Tool to fetch a specific product group by ID.

List Barcodes

Tool to retrieve a list of barcodes.

List Bundle Items

Tool to retrieve a list of bundle items.

List Clusters

Tool to retrieve a list of clusters from Booqable.

List Coupons

Tool to retrieve a list of coupons.

List Default Properties

Tool to retrieve a list of default properties from Booqable.

List Documents

Tool to retrieve a list of documents.

List Email Templates

Tool to list email templates from Booqable.

List Employees

Tool to retrieve a list of employees from Booqable.

List Inventory Breakdowns

Tool to retrieve a list of inventory breakdowns filtered by status and product/product group.

List Items

Tool to retrieve a list of items (products and product groups).

List Lines

Tool to retrieve a paginated list of lines from orders.

List Locations

Tool to retrieve a list of locations from Booqable.

List Notes

Tool to retrieve a list of notes.

List Orders

Tool to retrieve a paginated list of orders.

List Payment Methods

Tool to retrieve a list of payment methods from Booqable.

List Payments

Tool to list all payments from Booqable.

List Photos

Tool to retrieve a paginated list of photos from Booqable.

List Plannings

Tool to retrieve planning records that track product and bundle reservations across locations and time periods.

List Price Rulesets

Tool to list price rulesets.

List Price Structures

Tool to list price structures.

List Product Groups

Tool to list product groups from Booqable API v4.

List Products

Tool to retrieve a list of products.

List Properties

Tool to retrieve a list of properties.

List Provinces

Tool to retrieve a list of provinces.

List Stock Item Plannings

Tool to retrieve a list of stock item plannings.

List Stock Items

Tool to retrieve a list of stock items.

List Tax Rates

Tool to retrieve a list of tax rates.

List Tax Values

Tool to retrieve a list of tax values.

List Users

Tool to retrieve a list of users from Booqable.

Search Bundles

Tool to search bundles with advanced filtering.

Search Customers

Tool to search customers in the Booqable system.

Search Documents

Tool to search documents using advanced filtering with logical operators.

Search Items

Tool to search items (products and bundles) with advanced filtering.

Search Orders

Tool to search orders with advanced filtering using logical operators.

Search Plannings

Tool to search plannings with advanced filtering.

Update Company

Tool to update the current company's information in Booqable.

FAQ

Frequently asked questions

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

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

Start with Booqable.It takes 30 seconds.

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

Start building