SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Enigma MCP with Autogen

Connect Autogen to Enigma MCP. Verify the legitimacy of acme corp in delaware, check if a business is on any u.s. sanctions list, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Enigma logoEnigma
Api Key

Enigma provides trusted data on U.S. businesses, including identity, firmographics, and financial health. It helps sales, marketing, and risk teams make smarter, faster decisions.

19 Tools

Introduction

This guide walks you through connecting Enigma to AutoGen using the Composio tool router. By the end, you'll have a working Enigma agent that can verify businesses with KYB, screen against sanctions and watchlists, match business profiles, search entities with GraphQL, and manage lists through natural language commands.

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

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

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

The Enigma MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Enigma account. It provides structured and secure access to comprehensive U.S. business data, so your agent can perform actions like verifying company identities, screening for compliance, and assessing financial health automatically.

  • Automated KYB business verification: Rapidly verify the legitimacy of U.S. businesses by checking official state records, brands, and legal entities through your agent.
  • Sanctions and watchlist screening: Instantly screen businesses and transactions against up-to-date sanctions and watchlists for enhanced compliance and risk mitigation.
  • Retrieve detailed business intelligence: Access comprehensive profiles on businesses, including best match results, affiliated brands, and entity structures.
  • Compliance automation: Let your agent independently run verification checks and screenings to streamline onboarding, due diligence, and regulatory workflows.

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

Supported Tools

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

Create List

Tool to create a new list to organize and group entities in Enigma.

Create Suggestion

Tool to create a suggestion for data correction, enhancement, or analysis feedback in Enigma.

Delete List

Tool to delete an existing list permanently from the system.

Get Account Information

Tool to retrieve information about the current API account via GraphQL.

Get Aggregate Counts

Get aggregate counts of operating locations and their associated brands or legal entities.

Get Attribute Groups

Tool to retrieve attribute groups for Enigma entity types.

Get Background Task Status

Tool to get the status and results of a background task by ID.

Get Business by Enigma ID

Tool to retrieve detailed business information using an Enigma ID.

Get Screening Decision

Tool to retrieve a screening decision by its request ID.

Get Extended GraphQL Schema

Tool to retrieve extended schema information for Enigma's GraphQL API.

Get List Materialization

Retrieve a list materialization by ID, including its status, progress, and results location when available.

Get Sanctioned Entity Details

Retrieve information about a specific OFAC sanctioned entity by collection and record ID.

KYB Business Verification

Perform a Know Your Business (KYB) check on a US business using Enigma's legal entity data.

List Screening Decisions

Tool to retrieve multiple screening decisions with pagination and filtering options.

Match Business Profile

Tool to match business records against Enigma's SMB data asset using fuzzy matching on business name and location.

Screen Against Sanctions and Watchlists

A tool to screen customers and transactions against sanctions and other watchlists.

Search Enigma Entities via GraphQL

Search Enigma for brands, operating locations, or legal entities by name, phone, website, or TIN, optionally narrowed by address.

Search User-Created Lists

Tool to search and retrieve user-created lists via GraphQL.

Verify Business Identity (KYB v2)

Verify business identity using Enigma's KYB v2 endpoint for compliance or risk assessment.

FRAMEWORKS

How to build Enigma MCP Agent with another framework

Claude Code logo

Claude Code

Use Enigma MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Enigma MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Enigma MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Enigma MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Enigma MCP with Grok Bot

Codex logo

Codex

Use Enigma MCP with Codex

OpenClaw logo

OpenClaw

Use Enigma MCP with OpenClaw

Hermes logo

Hermes

Use Enigma MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Enigma MCP with Atomic Agent

Google ADK logo

Google ADK

Use Enigma MCP with Google ADK

LangChain logo

LangChain

Use Enigma MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Enigma MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Enigma MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Enigma MCP with LlamaIndex

CrewAI logo

CrewAI

Use Enigma MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Enigma MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Enigma.It takes 30 seconds.

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

Start building