SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Findymail MCP with Autogen

Connect Autogen to Findymail MCP. Find verified email for john at acme.com, create a new contact list for leads, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Findymail logoFindymail
Api Key

Findymail is a B2B data provider offering verified email and phone contacts for sales prospecting. Enhance outreach with automated exports, email verification, and CRM enrichment.

21 Tools

Introduction

This guide walks you through connecting Findymail to AutoGen using the Composio tool router. By the end, you'll have a working Findymail agent that can find emails by name, verify emails, manage contact and exclusion lists, search Intellimatch, and check your credits through natural language commands.

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

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

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

The Findymail MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Findymail account. It provides structured and secure access to verified B2B contact data, so your agent can create and manage contact lists, find and verify emails, and streamline your outreach workflow automatically.

  • Automated contact list management: Let your agent create new contact lists, fetch all your lists, or delete lists as your prospecting needs change.
  • Precise contact discovery: Ask your agent to find and retrieve emails for prospects based on full name and company domain, making it easier to build targeted outreach campaigns.
  • Bulk contact retrieval: Direct your agent to list all contacts within a specific list, enabling quick access to leads for export or follow-up.
  • Email deliverability verification: Have your agent check if an email address is valid and safe to use before sending that crucial first message.
  • Seamless CRM enrichment: Use verified contact details to automatically enrich your CRM, helping you keep data accurate and actionable for your sales team.

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

Supported Tools

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

Add Excluded Domain

Add domains to Findymail exclusions used by Intellimatch searches.

Create Exclusion List

Create a named exclusion list for the authenticated user to organize websites excluded from Intellimatch searches.

Create Contact List

Tool to create a new contact list.

Delete Exclusion List

Delete an Intellimatch exclusion list by ID and all its associated domains.

Delete Contact List

Permanently deletes a contact list by its ID.

Find Email by Name

Find a person's email using their full name and company domain or company name.

Get Contact Lists

Tool to retrieve all contact lists.

Get Credits

Check the team's remaining Findymail credit balance before running operations.

Get Credits Summary

Tool to retrieve credits usage summary report for the authenticated account.

Get Credits Team Summary

Retrieve the team's credit usage summary for the default reporting period, including totals and usage by team member.

Get Exclusion List

Retrieve metadata for an exclusion list by ID, without its domains.

Get Intellimatch Data

Retrieve the default first page of company data from a completed Intellimatch search by hash.

Get Intellimatch Status

Tool to check the status of an Intellimatch search job.

List Contacts

Tool to retrieve contacts from a specified list (paginated).

List Excluded Domains

Retrieve a page of globally excluded domains for Intellimatch searches.

List Exclusion Lists

Tool to retrieve all exclusion lists for managing excluded websites from Intellimatch searches.

Remove Excluded Domain

Remove excluded domains by ID from Intellimatch exclusion lists.

Search Intellimatch

Start an Intellimatch company search using a natural-language query, optionally finding contacts and emails.

Update Exclusion List

Rename an existing exclusion list.

Update Contact List

Update an existing Findymail contact list's name and team-sharing setting.

Verify Email

Verify the deliverability of an email address before outreach.

FRAMEWORKS

How to build Findymail MCP Agent with another framework

Claude Code logo

Claude Code

Use Findymail MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Findymail MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Findymail MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Findymail MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Findymail MCP with Grok Bot

Codex logo

Codex

Use Findymail MCP with Codex

OpenClaw logo

OpenClaw

Use Findymail MCP with OpenClaw

Hermes logo

Hermes

Use Findymail MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Findymail MCP with Atomic Agent

Google ADK logo

Google ADK

Use Findymail MCP with Google ADK

LangChain logo

LangChain

Use Findymail MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Findymail MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Findymail MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Findymail MCP with LlamaIndex

CrewAI logo

CrewAI

Use Findymail MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Findymail MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Findymail.It takes 30 seconds.

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

Start building