SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Cloudlayer MCP with Autogen

Connect Autogen to Cloudlayer MCP. Generate pdf from a contract html template, convert a marketing webpage to a png image, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Cloudlayer logoCloudlayer
Api Key

Cloudlayer is a document and asset generation service for creating PDFs and images via API or SDKs. It lets you automate high-quality doc creation, saving dev time and reducing manual work.

16 Tools

Introduction

This guide walks you through connecting Cloudlayer to AutoGen using the Composio tool router. By the end, you'll have a working Cloudlayer agent that can convert HTML and URLs to PDF, capture URLs as images, generate PDFs from templates, and track jobs and assets through natural language commands.

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

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

Also integrate Cloudlayer with

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

The Cloudlayer MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cloudlayer account. It provides structured and secure access to dynamic document and asset generation, so your agent can perform actions like converting HTML or URLs to PDFs or images, managing assets, and configuring storage on your behalf.

  • Automated PDF and image generation: Instantly convert HTML content or public URLs into professional PDFs and images for reporting, documentation, or sharing.
  • Asset management and retrieval: Let your agent fetch metadata or download links for generated assets, or list your most recent document and image creations.
  • Dynamic storage configuration: Seamlessly add and manage external storage buckets or containers for organizing generated files and assets.
  • Real-time API health monitoring: Enable your agent to check Cloudlayer API status, ensuring your integrations are always up and running.
  • Flexible screenshot and rendering tasks: Capture dynamic webpage screenshots as images or PDFs, with full control over conversion parameters, for advanced automation workflows.

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

Supported Tools

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

Add Storage

Add a user-owned S3-compatible storage configuration for storing generated assets.

Convert HTML to Image (V2)

Convert HTML content to a PNG, JPG, or WebP image using the v2 API, with viewport configuration, transparency, auto-scroll, and custom wait conditions.

Convert HTML to PDF (v2)

Tool to convert HTML content to PDF using CloudLayer v2 API.

Convert URL to PDF (Simple)

Convert a URL to PDF using a GET request with minimal parameters.

Delete Storage Configuration

Delete a user storage configuration by its ID.

Get Account Info

Tool to retrieve Cloudlayer account usage, credits, and document counts.

Get Asset

Tool to retrieve a specific asset by its ID.

Get Job By ID

Retrieve details of a specific Cloudlayer job by its ID.

Get API Status

Tool to test API reachability.

Get Storage Configuration by ID

Tool to retrieve a specific storage configuration by its ID.

List Assets

List assets in your CloudLayer account with cursor-based pagination.

List Jobs

List jobs in your CloudLayer account with cursor-based pagination.

List Storage Configurations

Retrieves all user storage configurations (S3-compatible buckets) for the authenticated Cloudlayer account.

Template to PDF

Generate a PDF document from an HTML/Nunjucks template with dynamic data.

Convert URL to Image

Converts a webpage URL to an image (PNG, JPG, or WebP).

Convert URL to PDF

Convert a URL to PDF using a POST request, with options for paper size, margins, headers, and footers.

FRAMEWORKS

How to build Cloudlayer MCP Agent with another framework

Claude Code logo

Claude Code

Use Cloudlayer MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Cloudlayer MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Cloudlayer MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Cloudlayer MCP with Claude Agent SDK

Codex logo

Codex

Use Cloudlayer MCP with Codex

OpenClaw logo

OpenClaw

Use Cloudlayer MCP with OpenClaw

Hermes logo

Hermes

Use Cloudlayer MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Cloudlayer MCP with Atomic Agent

Google ADK logo

Google ADK

Use Cloudlayer MCP with Google ADK

LangChain logo

LangChain

Use Cloudlayer MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Cloudlayer MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Cloudlayer MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Cloudlayer MCP with LlamaIndex

CrewAI logo

CrewAI

Use Cloudlayer MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Cloudlayer MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Cloudlayer.It takes 30 seconds.

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

Start building