How to integrate Imagekit io MCP with Autogen

GET STARTED FOR FREE
Framework Integration Gradient
Imagekit io Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Imagekit io to AutoGen using the Composio tool router. By the end, you'll have a working Imagekit io agent that can move all event photos to new 2024 folder, delete outdated logo file from media library, create custom metadata field for copyright info, copy marketing assets folder to backup location through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Imagekit io account through Composio's Imagekit io 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 Imagekit io
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Imagekit io tools
  • Run a live chat loop where you ask the agent to perform Imagekit io 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 Imagekit io MCP server, and what's possible with it?

The Imagekit io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your ImageKit.io account. It provides structured and secure access to your media library, so your agent can perform actions like organizing folders, managing files, handling bulk operations, editing metadata, and cleaning up assets on your behalf.

  • Bulk file operations: Effortlessly move, copy, or update tags on multiple files at once to streamline large-scale asset management.
  • Folder organization and management: Ask your agent to create new folders for better asset structuring or delete old folders—including all their contents—when you need to tidy up.
  • Custom metadata control: Let your agent create or delete custom metadata fields, so your media assets stay rich with the information your workflows need.
  • File and version cleanup: Instruct the agent to permanently delete files or remove outdated file versions to keep your storage lean and organized.
  • Bulk job monitoring: Have your agent track the status of ongoing bulk jobs, like folder copies or moves, so you always know what’s happening behind the scenes.

Supported Tools & Triggers

Tools
Bulk Job StatusTool to check status of a bulk job.
Bulk Move FilesTool to move multiple files in bulk.
Bulk Remove TagsTool to remove tags from multiple files in bulk.
Copy FolderTool to initiate a bulk copy of a folder.
Create Custom Metadata FieldTool to create a custom metadata field.
Create FolderTool to create a new folder.
Delete Custom Metadata FieldTool to delete a custom metadata field.
Delete FileTool to delete a file.
Delete File VersionTool to delete a specific non-current file version.
Delete FolderTool to delete a folder.
Delete Multiple FilesTool to delete multiple files.
Get Upload Authentication ParametersTool to generate authentication parameters for client-side file uploads.
Get File DetailsTool to retrieve details of a specific file.
Get File MetadataTool to retrieve metadata of an uploaded file.
Get File Version DetailsTool to retrieve details of a specific file version.
Get UsageTool to retrieve account usage metrics.
List and Search AssetsTool to list and search assets in your ImageKit account.
List Custom Metadata FieldsTool to list all custom metadata fields.
List File VersionsTool to list all versions of a file.
Move FolderTool to initiate a bulk move of a folder.
Purge ImageKit CacheTool to purge CDN and ImageKit caches for a given URL.
Check purge cache statusTool to check the status of a cache purge request.
Rename FileTool to rename a file.
Restore File VersionTool to restore a specific non-current file version as the current one.
Update Custom Metadata FieldTool to update an existing custom metadata field.
Update File DetailsTool to update details of a file.

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

How to build Imagekit io MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Imagekit io MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Imagekit io MCP with Claude Agent SDK

Google ADK

Google ADK

Use Imagekit io MCP with Google ADK

LangChain

LangChain

Use Imagekit io MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Imagekit io MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Imagekit io MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Imagekit io MCP with LlamaIndex

CrewAI

CrewAI

Use Imagekit io MCP with CrewAI

Claude Code

Claude Code

Use Imagekit io MCP with Claude Code

FAQ

What are the differences in Tool Router MCP and Imagekit io MCP?

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

Can I manage the permissions and scopes for Imagekit io while using Tool Router?

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

Used by agents from

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