How to integrate Backendless MCP with Autogen

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

Introduction

This guide walks you through connecting Backendless to AutoGen using the Composio tool router. By the end, you'll have a working Backendless agent that can list all files in the user uploads folder, create a new directory for project assets, retrieve users where status is active, delete a file named report.pdf from backups through natural language commands.

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

The Backendless MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Backendless account. It provides structured and secure access to your backend services, so your agent can perform actions like managing file storage, retrieving and updating database records, handling directories, and orchestrating server-side logic on your behalf.

  • Dynamic file and directory management: Allow your agent to create, copy, delete, and list files or folders in your Backendless storage, keeping your app data organized.
  • Database record retrieval and filtering: Empower the agent to fetch objects from specific tables with advanced filtering, sorting, and pagination for instant data access.
  • Automated backend task scheduling: Let the agent create or delete timers to run recurring or one-off server-side logic, enabling powerful backend automation.
  • Custom Hive resource management: Instruct your agent to create new Backendless Hive resources and retrieve full maps of stored values for scalable, flexible data handling.
  • Safe data cleanup: Make it easy for your agent to remove obsolete files, directories, or scheduled tasks, helping maintain a tidy and efficient backend environment.

Supported Tools & Triggers

Tools
Copy FileTool to copy a file or directory within backendless file storage.
Create DirectoryTool to create a new directory at the specified path.
Create Backendless HiveTool to create a new hive.
Create Backendless TimerTool to create a new timer with schedule and code.
Delete DirectoryTool to delete a directory at the specified path in backendless file storage.
Delete FileTool to delete a file at the specified path in backendless file storage.
Delete Backendless TimerTool to delete a backendless timer by name.
Directory ListingTool to retrieve a listing of files and directories at a given path.
General Object RetrievalTool to retrieve objects from a specified backendless table with filtering, sorting, and pagination.
Get All ValuesTool to retrieve all values from a map in a specified hive.
Get Counter ValueTool to retrieve the current value of a backendless counter.
Get File CountTool to get the count of files in a backendless directory.
Get Key ItemsTool to retrieve values for a specified key in a list (all, single, or range).
Get Backendless TimerTool to retrieve information about a specific timer.
Map PutTool to set or update key-value pairs in a hive map.
Move FileTool to move a file or directory within backendless file storage.
Publish MessageTool to publish a message to a specified messaging channel.
Reset CounterTool to reset a backendless counter back to zero.
Set Counter ValueTool to set a backendless counter to a specific value conditionally.
Update Backendless TimerTool to update schedule or code of an existing timer.
Change User PasswordTool to change the password for the current user.
Delete UserTool to delete a user by user id.
Find User by IDTool to retrieve user information by id.
Grant Permission to UserTool to grant a permission to a user on a specific data object.
User LoginTool to log in a registered user with identity and password.
User LogoutTool to log out the currently authenticated user.
User Password RecoveryTool to initiate password recovery for a user.
User RegistrationTool to register a new user with email and password.
Revoke Permission from UserTool to revoke a permission from a specified user or role on a data table.
Update UserTool to update properties of an existing backendless user.
Validate User TokenTool to validate a user session token.

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

How to build Backendless MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Backendless MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Backendless MCP with Claude Agent SDK

Google ADK

Google ADK

Use Backendless MCP with Google ADK

LangChain

LangChain

Use Backendless MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Backendless MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Backendless MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Backendless MCP with LlamaIndex

CrewAI

CrewAI

Use Backendless MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Backendless 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 Backendless 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