How to integrate Companyenrich MCP with Autogen

This guide walks you through connecting Companyenrich to AutoGen using the Composio tool router. By the end, you'll have a working Companyenrich agent that can enrich openai company profile by domain, find companies similar to stripe, search cybersecurity startups in berlin through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Companyenrich account through Composio's Companyenrich MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Companyenrich logoCompanyenrich
Api Key

Companyenrich is a company data API for enrichment, search, and similar company discovery. Use it to turn domains or company names into clean business profiles fast.

32 Tools

Introduction

This guide walks you through connecting Companyenrich to AutoGen using the Composio tool router. By the end, you'll have a working Companyenrich agent that can enrich openai company profile by domain, find companies similar to stripe, search cybersecurity startups in berlin through natural language commands.

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

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

Also integrate Companyenrich with

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

The Companyenrich MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Companyenrich account. It provides structured and secure access so your agent can perform Companyenrich operations on your behalf.

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

Supported Tools

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

Autocomplete Companies

Returns a list of companies matching the given partial domain name.

Autocomplete Keywords

Lookup keywords for use in company search filters.

Autocomplete Positions

Lookup positions/job titles for use in people search filters.

Autocomplete Technologies

Lookup technologies for use in company search filters.

Count companies matching search criteria

Returns the total count of companies matching the given search criteria without retrieving the actual results.

Count Similar Companies

Tool to count the total number of similar companies matching the given search criteria without retrieving the actual results.

Create people search export job

Creates an asynchronous search export job for up to 50,000 people.

Create search export job

Creates an asynchronous search export job for company data.

Enrich company by domain

Enriches a company using its domain name as lookup parameter.

Enrich company by properties

Enriches a company using its properties.

Batch Enrich Companies

Enriches a list of companies using their domain names.

Find Similar Companies

Tool to find similar companies to the given company by domain.

Get Bulk Enrichment Job Status

Returns the current status of a bulk enrichment job.

Get Company Workforce

Returns workforce insights for a single company.

Get Country by Code

Tool to search for a country by its ISO 3166-1 alpha-2 code.

Get Current User

Returns information about the authenticated user, including their API key, credit balance, and account capabilities.

Get Job Details

Returns details for a specific job by ID.

Get People Search Export Job Status

Returns the current status of a person search export job.

Get Regions

Tool to get all available regions.

Get search export job status

Returns the current status of a search export job.

List all jobs

Returns a paginated list of all jobs (bulk enrichment, etc.

List bulk enrichment jobs

Returns a paginated list of all bulk enrichment jobs for the authenticated user.

List Industries

Obtain a list of all company industries.

List Person Search Export Jobs

Returns a paginated list of all person search export jobs for the authenticated user.

List search export jobs

Returns a paginated list of all search export jobs for the authenticated user.

Lookup Person by Email

Look up a person by email address.

Search people with cursor pagination

Searches people based on given criteria using cursor-based pagination.

Search cities by name or country

Search for cities by name or country codes.

Search companies by criteria

Searches companies based on given criteria.

Search Countries

Tool to search countries by name.

Search People

Searches people based on given criteria using page-based pagination.

Search States

Tool to search states by name or country codes.

FAQ

Frequently asked questions

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

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

Start with Companyenrich.It takes 30 seconds.

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

Start building