How to integrate Ipdata co MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Ipdata co Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Ipdata co to AutoGen using the Composio tool router. By the end, you'll have a working Ipdata co agent that can get city and country for this ip address, check if this ip is from the eu, find mobile carrier for a given ip, show my api usage count for today through natural language commands.

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

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

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

The Ipdata co MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ipdata co account. It provides structured and secure access to IP geolocation, carrier, and threat intelligence data, so your agent can perform actions like IP lookups, ASN analysis, carrier identification, and usage monitoring on your behalf.

  • Comprehensive IP lookups: Instantly retrieve detailed location, ownership, and threat profile information for any IP address worldwide.
  • Advanced ASN intelligence: Dive deep into network data by performing advanced ASN lookups to get prefixes, peer relationships, and registry details for a given ASN number.
  • Carrier and telecom insights: Fetch mobile carrier data—including carrier name, MCC, and MNC—for specific IPs to help identify network providers or mobile origins.
  • EU-specific IP processing: Ensure data residency compliance by performing IP lookups processed and stored exclusively within the EU.
  • API usage monitoring: Easily check your API request counts from the last 24 hours to stay on top of your Ipdata co usage and quotas.

Supported Tools & Triggers

Tools
Advanced ASN LookupTool to perform advanced ASN lookup returning prefixes, peers, and registry details.
Get Carrier Data for an IPTool to return mobile carrier data for a specific IP.
EU-specific IP lookupTool to lookup a specific IP address via the EU-only data residency endpoint.
IPData: Calling CodeTool to fetch the international calling_code for an IP's country.
IPDATA Field CarrierTool to return only the carrier object for the calling IP.
Get City from IPTool to return only city for an IP.
IPData: Continent CodeTool to return only continent_code for an IP.
Get Continent Name from IPTool to return only continent name for an IP.
IPDATA Field CountTool to return only the request count made by your API key in the last 24 hours.
IPData: Country CodeTool to return only country_code for an IP.
Get Country Name from IPTool to return only country name for an IP.
IPDATA Field CurrencyTool to return only currency object for an IP.
Get Emoji Flag from IPTool to return only emoji flag for an IP.
Get Emoji Unicode from IPTool to return only emoji_unicode for an IP.
IPData: IPTool to return only the caller’s IP string.
IPData: Is EUTool to return only is_eu for an IP.
IPData: LanguagesTool to return only the languages array for an IP.
IPData: LatitudeTool to return only the latitude for an IP.
Get Longitude from IPTool to return only longitude for an IP.
IPData: Postal CodeTool to return only postal code for an IP.
Get Region from IPTool to return only region for an IP.
IPData: Region CodeTool to return only region_code for an IP.
Get Threat for IPTool to return only the threat object for the calling IP.
IPData: Time ZoneTool to return only the time_zone object for an IP.
Get Currency for IPTool to retrieve currency information for a specific IP.
IPData Basic ASN for IPTool to return basic ASN data for a specific IP.
IPData Bulk Lookup V1Tool to bulk lookup up to 100 IP addresses via ipdata.
Get company data for IPTool to retrieve company data for a given IP address.
EU-only calling IP lookupTool to lookup the calling client IP via EU-residency endpoint.
IPData Lookup IP V1Tool to lookup comprehensive IP information (geolocation, network, company, and threat data) in one call.
IPData Threat for IPTool to return threat intelligence data for a specific IP.
IPData Time Zone for IPTool to return timezone data for a specific IP.
Lookup Calling IPTool to lookup full data for the calling client IP.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router 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 Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router 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

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Ipdata co account you can connect to Composio
  • Some basic familiarity with Autogen and Python async

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.

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 Ipdata co via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Ipdata co connections to use

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 Ipdata co session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["ipdata_co"]
    )
    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 Ipdata co tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Ipdata co assistant agent with MCP tools
    agent = AssistantAgent(
        name="ipdata_co_assistant",
        description="An AI assistant that helps with Ipdata co 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 Ipdata co tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Ipdata co 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 Ipdata co 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 Ipdata co 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 Ipdata co session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["ipdata_co"]
    )
    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 Ipdata co assistant agent with MCP tools
        agent = AssistantAgent(
            name="ipdata_co_assistant",
            description="An AI assistant that helps with Ipdata co 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 Ipdata co 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 Ipdata co 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 Ipdata co, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Ipdata co MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Ipdata co MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ipdata co MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ipdata co MCP with Google ADK

LangChain

LangChain

Use Ipdata co MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Ipdata co MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Ipdata co MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ipdata co MCP with LlamaIndex

CrewAI

CrewAI

Use Ipdata co MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Ipdata co MCP?

With a standalone Ipdata co MCP server, the agents and LLMs can only access a fixed set of Ipdata co tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Ipdata co and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with Autogen?

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 Ipdata co tools.

Can I manage the permissions and scopes for Ipdata co while using Tool Router?

Yes, absolutely. You can configure which Ipdata co 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.

How safe is my data with Composio Tool Router?

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 Ipdata co data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free