How to integrate Apaleo MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Apaleo Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Apaleo to AutoGen using the Composio tool router. By the end, you'll have a working Apaleo agent that can archive a property that's no longer active, clone existing property for new location, create a new unit group for suites, check if a specific unit exists through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Apaleo account through Composio's Apaleo 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 Apaleo
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Apaleo tools
  • Run a live chat loop where you ask the agent to perform Apaleo 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 Apaleo MCP server, and what's possible with it?

The Apaleo MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Apaleo account. It provides structured and secure access to your property management operations, so your agent can perform actions like managing properties, handling units, checking availability, and automating setup tasks on your behalf.

  • Property management and archiving: Enable your agent to create, clone, or archive properties, letting you quickly scale or reorganize your portfolio as your business evolves.
  • Unit and unit group operations: Let your agent create new units or unit groups, check if specific units exist, and manage all aspects of your inventory with ease.
  • Attribute and setup automation: Ask your agent to create or verify unit attributes, ensuring your property data is always up-to-date and consistent.
  • Bulk unit creation: Allow your agent to generate multiple units in one go, following custom naming rules, to save you time during onboarding or expansion.
  • Property cloning and rapid deployment: Have your agent clone existing properties with all inventory and rate plans, making it simple to launch new locations based on proven setups.

Supported Tools & Triggers

Tools
Archive a propertyUse this endpoint to archive an existing live property this operation set the isarchived flag to trueyou must have at least one of these scopes: 'properties.
Check if a property existsCheck if a property exists by id.
Check if a unit attribute existsCheck if a unit attribute existsyou must have at least one of these scopes: 'unitattributes.
Check if a unit existsCheck if a unit exists by id.
Check if a unit group existsCheck if a unit group exists by id.
Clones a propertyUse this call to clone a specific property.
Create a unitUse this call to create a new unit.
Create a unit attributeUse this call to create a new unit attribute.
Create a unit groupUse this call to create a new unit group.
Create multiple unitsUse this call to create multiple units, following a naming rule.
Creates a propertyUse this call to create a new property.
Delete a unitUse this call to delete a unit.
Delete a unit groupUse this call to delete a unit group.
Deletes unit attributeDeletes unit attributeyou must have at least one of these scopes: 'unitattributes.
Get a properties listGet the list of properties.
Get a propertyGet a property by id.
Get a unitGet a unit by id.
Get a unit groupGet a unit group by id.
Get a units listGet the list of units.
Get unit attribute by idGet unit attribute by idyou must have at least one of these scopes: 'unitattributes.
Get unit attribute listGet unit attribute listyou must have at least one of these scopes: 'unitattributes.
List Unit GroupsGet the list of unit groups.
Move property to liveUse this endpoint to move an existing test property to live this operation changes the property status to 'live'you must have at least one of these scopes: 'properties.
Replace a unit groupUse this call to modify a unit group.
Reset Property DataThis endpoint deletes transactional data for a property in 'test' status.
Returns a list of supported countriesReturns a list of iso country codes that could be used to create properties.
Returns number of unit groupsReturns number of unit groups matching the filter criteriayou must have at least one of these scopes: 'unitgroups.
Returns number of unitsReturns number of units matching the filter criteriayou must have at least one of these scopes: 'units.
Return total count of propertiesReturn total count of propertiesyou need to be authorized (no particular scope required)

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

How to build Apaleo MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Apaleo MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Apaleo MCP with Claude Agent SDK

Google ADK

Google ADK

Use Apaleo MCP with Google ADK

LangChain

LangChain

Use Apaleo MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Apaleo MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Apaleo MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Apaleo MCP with LlamaIndex

CrewAI

CrewAI

Use Apaleo MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Apaleo 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 Apaleo 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.

Book a call↗Get started for free