SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Clearout MCP with Autogen

Connect Autogen to Clearout MCP. Validate a list of emails for deliverability, check if this email is a business account, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Clearout logoClearout
Api Key

Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.

21 Tools

Introduction

This guide walks you through connecting Clearout to AutoGen using the Composio tool router. By the end, you'll have a working Clearout agent that can verify email addresses, run bulk verification jobs, find emails in bulk, look up people and companies, and check your credits through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

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

The Clearout MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Clearout account. It provides structured and secure access to email validation, prospecting, and enrichment tools, so your agent can perform actions like verifying email addresses, finding business contacts, checking domain details, and bulk-processing lists on your behalf.

  • AI-powered email verification: Instantly validate single or bulk email addresses to ensure deliverability and reduce bounce rates.
  • Email prospecting and enrichment: Find emails for people or companies, complete missing contact data, and verify if accounts are business or personal.
  • Domain and company intelligence: Retrieve company domains from names, fetch MX records, or pull WHOIS information to understand your leads and their infrastructure.
  • Disposable and catch-all detection: Check if an email is temporary or if a domain accepts all mail, helping you maintain list quality and avoid spam traps.
  • Bulk job automation: Upload, process, monitor, cancel, and download results for large-scale email finding and verification tasks, all through your agent.

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

Supported Tools

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

Autocomplete Company to Domain

Tool to autocomplete company names to probable domains with confidence scores.

Business Account Verify

Tool to check if an email belongs to a business/work account.

Catch-All Verify

Tool to check if an email domain is catch-all.

Verify Disposable Email

Tool to check if an email is from a disposable provider.

Find Domain MX Records

Tool to retrieve MX records for a domain in priority order.

Fetch Domain WHOIS Information

Tool to fetch WHOIS record for a domain.

Bulk Email Finder

Tool to upload a CSV or XLSX contacts file for bulk email finding.

Cancel Bulk Email Finder Job

Tool to cancel a running bulk email finder job.

Bulk Email Finder Result Download

Tool to generate a bulk email finder result download URL.

Bulk Email Verify

Tool to upload a CSV or XLSX file for bulk email verification.

Cancel Bulk Email Verification Job

Cancel an in-progress bulk email verification job.

Bulk Email Verify Progress Status

Tool to retrieve progress for a bulk email verification job.

Bulk Email Verify Result Download

Tool to obtain a temporary URL for bulk email verification results.

Email Verify Get Credits

Tool to fetch available email verification credits.

Instant Email Verifier

Tool to instantly verify a single email address.

Verify Free Email Account

Tool to detect if an email is from a free email service provider.

Verify Gibberish Email

Tool to verify if an email address is gibberish.

Reverse Lookup Company by Domain

Find company information (name, logo, LinkedIn URL, address) by looking up its domain name.

Reverse Lookup Person by Email

Tool to retrieve a person’s profile from an email address.

Find Person via LinkedIn URL

Tool to discover person information via a LinkedIn profile URL.

Role Account Verifier

Tool to determine if an email is a role-based account.

FRAMEWORKS

How to build Clearout MCP Agent with another framework

Claude Code logo

Claude Code

Use Clearout MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Clearout MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Clearout MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Clearout MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Clearout MCP with Grok Bot

Codex logo

Codex

Use Clearout MCP with Codex

OpenClaw logo

OpenClaw

Use Clearout MCP with OpenClaw

Hermes logo

Hermes

Use Clearout MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Clearout MCP with Atomic Agent

Google ADK logo

Google ADK

Use Clearout MCP with Google ADK

LangChain logo

LangChain

Use Clearout MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Clearout MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Clearout MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Clearout MCP with LlamaIndex

CrewAI logo

CrewAI

Use Clearout MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Clearout MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Clearout.It takes 30 seconds.

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

Start building