SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Tomba MCP with Autogen

Connect Autogen to Tomba MCP. Find all leads from example.com domain, check if this email is disposable, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Tomba logoTomba
Api Key

Tomba is an Email Finder for B2B sales and email marketing. Find and verify professional emails to boost your outreach results.

25 Tools

Introduction

This guide walks you through connecting Tomba to AutoGen using the Composio tool router. By the end, you'll have a working Tomba agent that can find professional emails, verify email addresses, enrich people and companies, search domain contacts, and manage lead lists through natural language commands.

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

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

Also integrate Tomba with

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

The Tomba MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Tomba account. It provides structured and secure access to your B2B email finding, lead management, and account configuration tools, so your agent can perform actions like discovering leads, managing lists, validating domains, and monitoring account usage on your behalf.

  • Lead discovery and enrichment: Ask your agent to list available lead attributes or add new leads directly into your Tomba account for streamlined outreach.
  • Lead list management: Effortlessly retrieve, update, or delete lead lists, helping you stay organized and keep your data current.
  • Domain validation and status checks: Have your agent check if a domain is webmail or disposable to ensure better deliverability and lead quality.
  • API key and account management: Direct your agent to list, create, or revoke API keys, and review usage statistics to keep your Tomba integration secure and efficient.
  • Usage monitoring and reporting: Let your agent fetch up-to-date API usage statistics, keeping you informed about your plan limits and consumption.

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

Supported Tools

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

List Lead Attributes

Retrieves all custom lead attributes defined in your Tomba account.

Domain Status

Tool to check if a domain is webmail or disposable.

Enrich Company

Enrich one company from its domain; this does not look up a specific person.

Enrich Person

Enrich one person from an email address; use the company or combined actions for company-only or one-call person-and-company data.

Enrich Person and Company

Enrich both a person and their company from one email in one request; use the focused actions when only one entity is needed.

Find Article Author

Find an article author's professional contact data from its URL.

Find Professional Email

Find a professional email from company and person identifiers, optionally requesting an associated mobile phone number on non-managed calls.

Find Email From LinkedIn

Find the most likely professional email from a LinkedIn profile URL, optionally requesting all associated emails and, on non-managed calls, mobile phone data.

Find Phone Numbers

Find phone numbers by providing at least one of email, domain, or LinkedIn URL.

Get Domain Email Count

Return contact counts and department breakdown for a domain.

Get Domain Email Formats

Return detected email patterns for a domain.

Get Email Sources

Return public web sources where an email address was found.

Get Employee Locations

Return employee counts by country for a domain.

Delete API Key by ID

Tool to delete an API key by its numeric ID.

List API Keys

Tool to list all API keys.

Create Lead

Create a new lead in Tomba's lead database.

List Leads

Tool to list all leads.

Delete Leads List by ID

Tool to delete a leads list by ID.

List Lead Lists

List your Tomba lead lists, with optional page and page-size controls.

Update Leads List

Tool to update a leads list's name by ID.

Search Domain Contacts

Search a domain or company for professional contacts, with optional mobile phone enrichment on non-managed calls.

Get Usage Statistics

Tool to get API usage statistics.

Validate Phone Number

Validate and format a phone number.

Verify Email

Verify email deliverability and mailbox signals, optionally requesting an associated mobile phone number on non-managed calls.

Verify Emails

Verify up to 1000 emails by managing Tomba's asynchronous bulk job synchronously, with per-email charges and account-plan rate limits.

FRAMEWORKS

How to build Tomba MCP Agent with another framework

Claude Code logo

Claude Code

Use Tomba MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Tomba MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Tomba MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Tomba MCP with Claude Agent SDK

Codex logo

Codex

Use Tomba MCP with Codex

OpenClaw logo

OpenClaw

Use Tomba MCP with OpenClaw

Hermes logo

Hermes

Use Tomba MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Tomba MCP with Atomic Agent

Google ADK logo

Google ADK

Use Tomba MCP with Google ADK

LangChain logo

LangChain

Use Tomba MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Tomba MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Tomba MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Tomba MCP with LlamaIndex

CrewAI logo

CrewAI

Use Tomba MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Tomba MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Tomba.It takes 30 seconds.

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

Start building