How to integrate HTML/CSS to Image MCP with Autogen

This guide walks you through connecting HTML/CSS to Image to AutoGen using the Composio tool router. By the end, you'll have a working HTML/CSS to Image agent that can render html as images, create images from templates, transform images, manage templates, and track usage through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a HTML/CSS to Image account through Composio's HTML/CSS to Image MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
HTML/CSS to Image logoHTML/CSS to Image
Api Key

HTML/CSS to Image is an API for converting HTML, CSS, URLs, and templates into images and PDFs. Use it to generate clean visual assets, screenshots, and documents without running browser infrastructure.

10 Tools

Introduction

This guide walks you through connecting HTML/CSS to Image to AutoGen using the Composio tool router. By the end, you'll have a working HTML/CSS to Image agent that can render html as images, create images from templates, transform images, manage templates, and track usage through natural language commands.

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

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

Also integrate HTML/CSS to Image with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The HTML/CSS to Image MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your HTML/CSS to Image account. It provides structured and secure access to your image generation, reusable templates, generated files, and usage data, so your agent can create images, render templates, transform files, manage templates, and monitor usage on your behalf.

  • HTML and webpage rendering: Have your agent turn HTML and CSS or public web pages into hosted images, including protected pages that require request headers.
  • Batch image creation: Direct your agent to generate up to 25 images at once from HTML, CSS, or web pages using shared or image-specific settings.
  • Reusable template management: Let the agent create Handlebars templates, list your existing templates, and update them with new HTML, CSS, or render settings.
  • Image retrieval and transformation: Instruct your agent to download generated images, convert their format, resize them, crop them, or permanently delete files you no longer need.
  • Account usage tracking: Have your agent review recent hourly, daily, monthly, and billing-period image usage for your connected account.

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

Supported Tools

Every HTML/CSS to Image action and event your agent gets out of the box.

Create Image

Create a hosted image from HTML/CSS or an internet-reachable webpage, including authenticated pages using request headers.

Create Image from Template

Create an image from a reusable template using the latest version or an explicitly selected version.

Create Images Batch

Create 1 to 25 hosted images from HTML/CSS or internet-reachable webpages in one request, including authenticated pages using shared or per-image headers.

Create Template

Create a reusable Handlebars HTML/CSS image template.

Delete Image

Permanently delete one generated image and clear its HCTI CDN cache.

Delete Images Batch

Permanently delete multiple generated images and clear their HCTI CDN caches.

Get or Transform Image

Download a generated image by ID, optionally converting its format, resizing it, or cropping it.

Get Usage

Return recent hourly, daily, monthly, and billing-period image usage for the connected account.

List Templates

List reusable image templates owned by the connected account, including their current version, source, and render settings.

Update Template

Create a new version of an existing template using replacement Handlebars HTML and optional CSS or render settings.

FRAMEWORKS

How to build HTML/CSS to Image MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use HTML/CSS to Image MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use HTML/CSS to Image MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use HTML/CSS to Image MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use HTML/CSS to Image MCP with Claude Cowork

Codex logo

Codex

Use HTML/CSS to Image MCP with Codex

OpenClaw logo

OpenClaw

Use HTML/CSS to Image MCP with OpenClaw

Hermes logo

Hermes

Use HTML/CSS to Image MCP with Hermes

CLI logo

CLI

Use HTML/CSS to Image MCP with CLI

Google ADK logo

Google ADK

Use HTML/CSS to Image MCP with Google ADK

LangChain logo

LangChain

Use HTML/CSS to Image MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use HTML/CSS to Image MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use HTML/CSS to Image MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use HTML/CSS to Image MCP with LlamaIndex

CrewAI logo

CrewAI

Use HTML/CSS to Image MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which HTML/CSS to Image 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 HTML/CSS to Image data and credentials are handled as safely as possible.

Start with HTML/CSS to Image.It takes 30 seconds.

Managed auth, hosted MCP servers, and every HTML/CSS to Image tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies