SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Cloudconvert MCP with Autogen

Connect Autogen to Cloudconvert MCP. Convert a pdf to word document format, export a converted file directly to s3, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Cloudconvert logoCloudconvert
Api Key

CloudConvert is a powerful file conversion service supporting over 200 file formats. It streamlines converting, compressing, and managing documents, media, and more, all in one place.

9 Tools

Introduction

This guide walks you through connecting Cloudconvert to AutoGen using the Composio tool router. By the end, you'll have a working Cloudconvert agent that can export files to S3 and Google Cloud Storage, list supported formats, track conversion tasks, and manage webhooks through natural language commands.

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

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

Also integrate Cloudconvert with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

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

The Cloudconvert MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your CloudConvert account. It provides structured and secure access to your file conversion workflows, so your agent can perform actions like converting files, exporting results to cloud storage, managing webhooks, and exploring supported formats on your behalf.

  • Seamless file conversion: Ask your agent to convert documents, images, audio, video, spreadsheets, or presentations between hundreds of supported formats automatically.
  • Automated export to cloud storage: Direct your agent to export converted files directly into your Google Cloud Storage or Amazon S3 buckets, streamlining storage and distribution.
  • Format discovery and optimization: Have the agent list all supported conversion formats, engines, and options, so you can choose the best settings for your needs.
  • Webhook management: Let your agent create, list, or delete webhooks to receive real-time notifications about conversion events and automate downstream processes.
  • Task tracking and user info: Retrieve detailed task histories, filter by status or date, and confirm the authenticated user’s account details for secure operations.

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

Supported Tools

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

Create Export Google Cloud Storage Task

Tool to create a task to export files to a Google Cloud Storage bucket.

Create Export S3 Task

Tool to create a task to export files to an Amazon S3 bucket.

Create Webhook

Creates a new webhook to receive CloudConvert event notifications.

Delete Webhook

Permanently delete a webhook by its ID.

List Operations

Tool to list all possible CloudConvert operations with their available options and engine details.

List Supported Formats

Tool to list all supported conversion formats, engines, and options.

List Tasks

List a page of CloudConvert tasks, with filters including status and job ID.

List Webhooks

List a page of existing webhooks, optionally filtered by URL, for inspection or management.

Show User

Retrieves the current authenticated user's CloudConvert account information.

FRAMEWORKS

How to build Cloudconvert MCP Agent with another framework

Claude Code logo

Claude Code

Use Cloudconvert MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Cloudconvert MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Cloudconvert MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Cloudconvert MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Cloudconvert MCP with Grok Bot

Codex logo

Codex

Use Cloudconvert MCP with Codex

OpenClaw logo

OpenClaw

Use Cloudconvert MCP with OpenClaw

Hermes logo

Hermes

Use Cloudconvert MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Cloudconvert MCP with Atomic Agent

Google ADK logo

Google ADK

Use Cloudconvert MCP with Google ADK

LangChain logo

LangChain

Use Cloudconvert MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Cloudconvert MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Cloudconvert MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Cloudconvert MCP with LlamaIndex

CrewAI logo

CrewAI

Use Cloudconvert MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Cloudconvert MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Cloudconvert.It takes 30 seconds.

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

Start building