SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Geoapify MCP with Autogen

Connect Autogen to Geoapify MCP. Find latitude and longitude for an address, suggest address completions as i type, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Geoapify logoGeoapify
Api Key

Geoapify is a comprehensive location-based services platform offering APIs for maps, geocoding, routing, and more. It enables developers to easily add powerful location capabilities and spatial intelligence to any application.

25 Tools

Introduction

This guide walks you through connecting Geoapify to AutoGen using the Composio tool router. By the end, you'll have a working Geoapify agent that can geocode addresses, autocomplete locations, plan routes and travel matrices, search nearby places, and generate static map images through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

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

The Geoapify MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Geoapify account. It provides structured and secure access to powerful location-based services, so your agent can perform actions like geocoding addresses, generating routes, fetching map tiles, and analyzing geographic data on your behalf.

  • Address autocomplete and geocoding: Instantly convert partial or full addresses into geographic coordinates, or fetch smart suggestions to speed up location entry.
  • Routing and reachability analysis: Generate routes, calculate reachable areas (isochrones/isodistances), and let your agent determine how far you can travel from a point within a set time or distance.
  • IP-based geolocation: Look up the approximate location of any IP address to enrich user data, personalize experiences, or detect regions automatically.
  • Map visualization and customization: Fetch custom-styled map tiles and create personalized marker icons for fully tailored map displays in your applications or reports.
  • Boundary and geometry operations: Retrieve administrative boundaries for any place or coordinate, and perform advanced geometric operations like combining or intersecting polygons to analyze spatial relationships.

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

Supported Tools

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

Address Autocomplete

Tool to fetch address suggestions based on partial input.

Batch Requests

Create or retrieve asynchronous batch processing jobs for geocoding, reverse geocoding, routing, or isoline APIs.

Get Boundaries Containing Location

Retrieve all administrative boundaries that contain a given location.

Create Batch Forward Geocode Job

Tool to create a batch forward geocoding job for up to 1000 addresses.

Create Batch Reverse Geocode Job

Tool to create a batch reverse geocoding job that converts multiple lat/lon coordinates into addresses asynchronously.

Forward Geocoding

Tool to convert an address into geographic coordinates.

Geometry Operation

Tool to perform geometric operations on stored polygon geometries.

Get Batch Forward Geocode Results

Retrieve completed batch forward geocoding results in JSON using a job ID.

Get Batch Reverse Geocode Results

Tool to retrieve batch reverse geocoding job results.

Get Child Boundaries (Consists Of)

Get boundaries that a specified location consists of.

Get Map Style JSON

Tool to retrieve vector map style JSON for MapLibre GL and Mapbox GL.

Generate Static Map Image

Tool to generate static map images with customizable style, size, center, zoom, markers, and geometries.

IP Geolocation

Lookup geographic location information for an IP address.

Generate isoline (isochrone/isodistance)

Tool to generate isochrone or isodistance isolines.

List Postcodes

Tool to list postcodes within a specified area or boundary.

Map Matching

Snap GPS traces to the road network for accurate route reconstruction.

Fetch Geoapify Map Tiles

Tool to fetch raster map tiles or style JSON from Geoapify.

Create Marker Icon

Generate custom map marker icons as PNG images.

Place Details

Tool to retrieve detailed information about a specific place.

Places Search

Search for points of interest (POIs) like restaurants, hotels, attractions, hospitals, etc.

Postcode Search

Tool to retrieve postcode information for a location.

Reverse Geocoding

Tool to reverse geocode coordinates into a structured address.

Route Matrix

Compute travel time and distance matrices between origin and destination coordinates.

Route Planner

Optimize multi-agent routes for deliveries, pickups, and service jobs.

Routing

Tool to calculate routes between multiple waypoints.

FRAMEWORKS

How to build Geoapify MCP Agent with another framework

Claude Code logo

Claude Code

Use Geoapify MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Geoapify MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Geoapify MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Geoapify MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Geoapify MCP with Grok Bot

Codex logo

Codex

Use Geoapify MCP with Codex

OpenClaw logo

OpenClaw

Use Geoapify MCP with OpenClaw

Hermes logo

Hermes

Use Geoapify MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Geoapify MCP with Atomic Agent

Google ADK logo

Google ADK

Use Geoapify MCP with Google ADK

LangChain logo

LangChain

Use Geoapify MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Geoapify MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Geoapify MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Geoapify MCP with LlamaIndex

CrewAI logo

CrewAI

Use Geoapify MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Geoapify MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Geoapify.It takes 30 seconds.

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

Start building