SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Codeinterpreter MCP with Autogen

Connect Autogen to Codeinterpreter MCP. Run this python script and show output, generate a line chart from your csv file, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Codeinterpreter logoCodeinterpreter
No Auth

Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.

5 Tools

Introduction

This guide walks you through connecting Codeinterpreter to AutoGen using the Composio tool router. By the end, you'll have a working Codeinterpreter agent that can create sandboxes, run Python code, execute terminal commands, and upload and fetch files through natural language commands.

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

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

Also integrate Codeinterpreter with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexOpenClawHermesAtomic 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 Codeinterpreter
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Codeinterpreter tools
  • Run a live chat loop where you ask the agent to perform Codeinterpreter 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 Codeinterpreter MCP server, and what's possible with it?

The Code Interpreter MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to Code Interpreter. It provides structured and secure access to Python coding environments, so your agent can create sandboxes, execute Python code, run terminal commands, upload source files, and retrieve generated files on your behalf.

  • Python sandbox creation: Have your agent create an isolated coding environment for data analysis, calculations, and prototyping.
  • Python code execution: Let the agent run Python scripts and collect results, output, and errors for further work.
  • Terminal command execution: Direct your agent to run terminal commands and use their output while completing coding tasks.
  • Input file uploads: Instruct your agent to upload datasets, scripts, or other files needed inside the coding environment.
  • Generated file retrieval: Have your agent retrieve reports, charts, processed datasets, or other files created during code execution.

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

Supported Tools

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

Create Sandbox

Create a sandbox to execute python code in a Jupyter notebook cell.

Execute Code

Execute python code in a sandbox and return any result, stdout, stderr, and error.

Get File

Get a file from the sandbox and returns the file.

Run Terminal Command

Run a command in the terminal and returns the stdout, stderr, and error code.

Upload File

Upload a file to the sandbox environment.

FRAMEWORKS

How to build Codeinterpreter MCP Agent with another framework

Claude Code logo

Claude Code

Use Codeinterpreter MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Codeinterpreter MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Codeinterpreter MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Codeinterpreter MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Codeinterpreter MCP with Grok Bot

Muse logo

Muse

Use Codeinterpreter MCP with Muse

Codex logo

Codex

Use Codeinterpreter MCP with Codex

OpenClaw logo

OpenClaw

Use Codeinterpreter MCP with OpenClaw

Hermes logo

Hermes

Use Codeinterpreter MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Codeinterpreter MCP with Atomic Agent

Google ADK logo

Google ADK

Use Codeinterpreter MCP with Google ADK

LangChain logo

LangChain

Use Codeinterpreter MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Codeinterpreter MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Codeinterpreter MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Codeinterpreter MCP with LlamaIndex

CrewAI logo

CrewAI

Use Codeinterpreter MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Codeinterpreter MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Codeinterpreter.It takes 30 seconds.

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

Start building