SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Cloudflare browser rendering MCP with Autogen

Connect Autogen to Cloudflare browser rendering MCP. Capture a full-page screenshot of example.com, extract all product prices from a category page, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Cloudflare browser rendering logoCloudflare browser rendering
Api Key

Cloudflare Browser Rendering lets you programmatically control headless browsers running on Cloudflare’s global network. It’s perfect for automating web interactions, capturing screenshots, and extracting web data at scale.

4 Tools

Introduction

This guide walks you through connecting Cloudflare browser rendering to AutoGen using the Composio tool router. By the end, you'll have a working Cloudflare browser rendering agent that can capture webpage screenshots, scrape HTML elements, and take page snapshots through natural language commands.

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

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

Also integrate Cloudflare browser rendering with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessGoogle 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 Cloudflare browser rendering
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Cloudflare browser rendering tools
  • Run a live chat loop where you ask the agent to perform Cloudflare browser rendering 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 Cloudflare browser rendering MCP server, and what's possible with it?

The Cloudflare browser rendering MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cloudflare browser rendering account. It provides structured and secure access to headless browser automation and rendering on Cloudflare’s global infrastructure, so your agent can capture screenshots, extract data, generate snapshots, and automate browser tasks on your behalf.

  • Automated webpage screenshot capture: Instantly instruct your agent to capture high-quality screenshots of any web page or HTML content with custom viewport and clipping options.
  • Combined DOM and visual snapshot generation: Direct your agent to create a full webpage snapshot with both the rendered HTML and an image, perfect for archiving or analysis.
  • Precise HTML element scraping: Ask your agent to extract specific text, HTML, attributes, or box metrics from rendered web pages using CSS selectors—ideal for detailed data collection or monitoring changes.
  • Account management automation: Enable your agent to fetch and manage all accessible Cloudflare accounts, making it easy to orchestrate browser rendering tasks across different environments.

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

Supported Tools

Every Cloudflare browser rendering action and event your agent gets out of the box.

Capture Screenshot

Tool to capture a webpage screenshot.

List Accounts

List Cloudflare accounts accessible to the authenticated API token, with optional name filtering and pagination.

Scrape HTML Elements

Tool to scrape HTML elements for text, HTML, attributes, and box metrics.

Take Webpage Snapshot

Capture both rendered HTML content and a screenshot of a webpage in a single request.

FRAMEWORKS

How to build Cloudflare browser rendering MCP Agent with another framework

Claude Code logo

Claude Code

Use Cloudflare browser rendering MCP with Claude Code

Cursor logo

Cursor

Use Cloudflare browser rendering MCP with Cursor

ChatGPT logo

ChatGPT

Use Cloudflare browser rendering MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Cloudflare browser rendering MCP with Claude Cowork

Antigravity logo

Antigravity

Use Cloudflare browser rendering MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Cloudflare browser rendering MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Cloudflare browser rendering MCP with Claude Agent SDK

Codex logo

Codex

Use Cloudflare browser rendering MCP with Codex

Grok Build logo

Grok Build

Use Cloudflare browser rendering MCP with Grok Build

VS Code logo

VS Code

Use Cloudflare browser rendering MCP with VS Code

OpenCode logo

OpenCode

Use Cloudflare browser rendering MCP with OpenCode

OpenClaw logo

OpenClaw

Use Cloudflare browser rendering MCP with OpenClaw

Hermes logo

Hermes

Use Cloudflare browser rendering MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Cloudflare browser rendering MCP with Atomic Agent

Pi logo

Pi

Use Cloudflare browser rendering MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Cloudflare browser rendering MCP with DeepSeek Harness

Google ADK logo

Google ADK

Use Cloudflare browser rendering MCP with Google ADK

LangChain logo

LangChain

Use Cloudflare browser rendering MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Cloudflare browser rendering MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Cloudflare browser rendering MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Cloudflare browser rendering MCP with LlamaIndex

CrewAI logo

CrewAI

Use Cloudflare browser rendering MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Cloudflare browser rendering MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Cloudflare browser rendering.It takes 30 seconds.

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

Start building