SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Builtwith MCP with Autogen

Connect Autogen to Builtwith MCP. Get all websites using shopify in 2024, show historical tech changes for example.com, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Builtwith logoBuiltwith
Api Key

BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.

10 Tools

Introduction

This guide walks you through connecting Builtwith to AutoGen using the Composio tool router. By the end, you'll have a working Builtwith agent that can look up website tech stacks, get financial and social data for domains, check redirects, and pull technology lead lists through natural language commands.

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

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

Also integrate Builtwith with

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

The Builtwith MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your BuiltWith account. It provides structured and secure access to web technology profiling and competitive intelligence data, so your agent can perform actions like analyzing website tech stacks, discovering competitor technologies, generating domain lists, and recommending similar sites on your behalf.

  • Comprehensive website technology profiling: Instantly analyze the current and historical tech stack of any website, including CMS, analytics, hosting, and more.
  • Bulk domain and technology list generation: Have your agent create and export lists of domains using specific technologies, or generate tailored files for large-scale research or outreach.
  • Competitor and product discovery: Identify financial, e-commerce, or product data for domains and uncover new market entrants or online retailers selling specific products.
  • Technology usage trends and datasets: Query historical datasets to track how specific technologies have been adopted across the internet over time, supporting market research and technology forecasting.
  • Intelligent site recommendations: Request suggestions for websites with similar technology profiles to a given domain, helping expand prospecting or research lists with relevant leads.

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

Supported Tools

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

Create Domain List File

Tool to create a TXT or ZIP file from a list of domains.

Datasets Lookup

Look up a technology's usage coverage and information through the BuiltWith Trends API, including live and expired site counts.

Domain API Lookup

Tool to retrieve current and historical technology information of a website.

Financial API Lookup

Tool to fetch financial data for a domain.

Free API Lookup

Tool to access last updated dates and counts for technology groups and categories for websites.

Lists API Get List

Tool to retrieve a list of websites using a specific technology.

Product API Lookup

Tool to find websites selling specific eCommerce products.

Recommendations API Lookup

Retrieve technology recommendations for a domain based on websites with similar technology profiles.

Redirects API Lookup

Tool to retrieve live and historical redirects for a website.

Social API Lookup

Tool to retrieve domains associated with social media profile URLs.

FRAMEWORKS

How to build Builtwith MCP Agent with another framework

Claude Code logo

Claude Code

Use Builtwith MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Builtwith MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Builtwith MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Builtwith MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Builtwith MCP with Grok Bot

Codex logo

Codex

Use Builtwith MCP with Codex

Kimi Code logo

Kimi Code

Use Builtwith MCP with Kimi Code

OpenClaw logo

OpenClaw

Use Builtwith MCP with OpenClaw

Hermes logo

Hermes

Use Builtwith MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Builtwith MCP with Atomic Agent

CLI logo

CLI

Use Builtwith MCP with CLI

Google ADK logo

Google ADK

Use Builtwith MCP with Google ADK

LangChain logo

LangChain

Use Builtwith MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Builtwith MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Builtwith MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Builtwith MCP with LlamaIndex

CrewAI logo

CrewAI

Use Builtwith MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Builtwith MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Builtwith.It takes 30 seconds.

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

Start building