How to integrate Artificial Analysis MCP with Autogen

Connect Autogen to Artificial Analysis MCP. Compare model pricing and latency, rank providers by coding benchmark scores, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Artificial Analysis logoArtificial Analysis
Api Key

Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.

12 Tools

Introduction

This guide walks you through connecting Artificial Analysis to AutoGen using the Composio tool router. By the end, you'll have a working Artificial Analysis agent that can compare model pricing and latency, rank providers by coding benchmark scores, find cheapest high-intelligence language models through natural language commands.

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

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

Also integrate Artificial Analysis with

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

The Artificial Analysis MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Artificial Analysis account. It provides structured and secure access so your agent can perform Artificial Analysis operations on your behalf.

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

Supported Tools

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

List Image-Editing Models (Arena)

List image-editing models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

List Image-to-Video-with-Audio Models (Arena)

List image-to-video-with-audio models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

List Image-to-Video Models (Arena)

List image-to-video models ranked by the Artificial Analysis image-to-video arena, with Elo score and 95% confidence interval.

List Language Models (Intelligence & Pricing)

List LLMs from the Artificial Analysis leaderboard with intelligence, coding and agentic indices, pricing, and performance (speed and latency).

List Instrumental Music Models (Arena)

List instrumental music-generation models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

List Music-with-Vocals Models (Arena)

List music-with-vocals generation models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

List Speech-to-Speech Models

List speech-to-speech models with Big Bench Audio (bba_score), Full Duplex Bench (fdb_score), and Tau-Voice (tau_voice_score) quality scores.

List Speech-to-Text Models (WER)

List speech-to-text (transcription) models with the Artificial Analysis overall word-error-rate index (aa_wer_index).

List Text-to-Image Models (Arena)

List text-to-image models ranked by the Artificial Analysis image arena, with Elo score and 95% confidence interval.

List Text-to-Speech Models (Arena)

List text-to-speech (TTS) models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

List Text-to-Video-with-Audio Models (Arena)

List text-to-video-with-audio models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

List Text-to-Video Models (Arena)

List text-to-video models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval.

FRAMEWORKS

How to build Artificial Analysis MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Artificial Analysis MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Artificial Analysis MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Artificial Analysis MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Artificial Analysis MCP with Claude Cowork

Codex logo

Codex

Use Artificial Analysis MCP with Codex

OpenClaw logo

OpenClaw

Use Artificial Analysis MCP with OpenClaw

Hermes logo

Hermes

Use Artificial Analysis MCP with Hermes

Google ADK logo

Google ADK

Use Artificial Analysis MCP with Google ADK

LangChain logo

LangChain

Use Artificial Analysis MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Artificial Analysis MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Artificial Analysis MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Artificial Analysis MCP with LlamaIndex

CrewAI logo

CrewAI

Use Artificial Analysis MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Artificial Analysis MCP with Pydantic AI

FAQ

Frequently asked questions

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

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

Start with Artificial Analysis.It takes 30 seconds.

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

Start building