How to integrate CarsXE MCP with Autogen

This guide walks you through connecting CarsXE to AutoGen using the Composio tool router. By the end, you'll have a working CarsXE agent that can decode vin and summarize vehicle specs, check recalls for a used car, estimate market value from license plate through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a CarsXE account through Composio's CarsXE MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
CarsXE logoCarsXE
Api Key

CarsXE is a vehicle data API platform for VIN specs, recalls, license plate decoding, market values, history, images, and automotive lookups. Use it to turn raw vehicle identifiers into clear, useful car data fast.

12 Tools

Introduction

This guide walks you through connecting CarsXE to AutoGen using the Composio tool router. By the end, you'll have a working CarsXE agent that can decode vin and summarize vehicle specs, check recalls for a used car, estimate market value from license plate through natural language commands.

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

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

Also integrate CarsXE with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The CarsXE MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your CarsXE account. It provides structured and secure access to vehicle specifications, records, valuations, images, and diagnostic data, so your agent can decode vehicles, check recalls and history, estimate market values, diagnose OBD codes, and recognize license plates on your behalf.

  • Vehicle identification and specifications: Have your agent decode a VIN or license plate, or look up detailed vehicle and trim information by year, make, and model.
  • Recall and safety checks: Instruct your agent to find safety recalls for a VIN or vehicle model, or submit and review recall checks for many VINs.
  • History, lien, and theft research: Let the agent retrieve title, salvage, insurance, lien, theft, VIN change, and historical title records for a vehicle.
  • Market values and diagnostics: Direct your agent to estimate wholesale, retail, and trade-in values or translate an OBD-II trouble code into a readable diagnosis.
  • Vehicle images and plate recognition: Have your agent find vehicle photos by make and model or analyze a public image for license plate candidates and detected vehicle details.

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

Supported Tools

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

Check Lien and Theft Records

Retrieve reportable US lien and theft events for a VIN.

Decode License Plate

Look up vehicle identity from a license plate using CarsXE's current global v2 decoder.

Decode OBD Code

Translate an OBD-II diagnostic trouble code into a readable diagnosis.

Get Vehicle Market Value

Estimate wholesale, retail, and trade-in values for a VIN using CarsXE's current v2 valuation, optionally adjusted for state, mileage, and condition.

Get Recall Batch

Make exactly one read request for a CarsXE recall batch.

Get Vehicle History

Retrieve title, brand, junk/salvage, insurance, VIN-change, and historical title records for a VIN.

Get Vehicle Images

Find up to 10 vehicle photos by make and model, with optional year, trim, angle, image type, size, color, quality, transparency, and license filters.

Get Vehicle Recalls

Find safety recall campaigns either for one VIN or for a year, make, and model.

Get Vehicle Specifications

Decode a 17-character VIN into vehicle identity, specifications, equipment, colors, and warranty data.

Get Year Make Model Data

Look up detailed vehicle and trim information by year, make, and model without a VIN.

Recognize License Plate

Analyze a publicly accessible vehicle image and return license-plate candidates, regions, confidence, bounding boxes, and detected vehicle details.

Submit Recall Batch

Create one asynchronous CarsXE recall-check batch for 1 to 10,000 VIN entries.

FRAMEWORKS

How to build CarsXE MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use CarsXE MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use CarsXE MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use CarsXE MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use CarsXE MCP with Claude Cowork

Codex logo

Codex

Use CarsXE MCP with Codex

OpenClaw logo

OpenClaw

Use CarsXE MCP with OpenClaw

Hermes logo

Hermes

Use CarsXE MCP with Hermes

CLI logo

CLI

Use CarsXE MCP with CLI

Google ADK logo

Google ADK

Use CarsXE MCP with Google ADK

LangChain logo

LangChain

Use CarsXE MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use CarsXE MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use CarsXE MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use CarsXE MCP with LlamaIndex

CrewAI logo

CrewAI

Use CarsXE MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with CarsXE.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies