How to integrate Composio search MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Composio search Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Composio search to AutoGen using the Composio tool router. By the end, you'll have a working Composio search agent that can find recent news about electric vehicles, search for top-rated hotels in paris, get latest stock info for apple, show upcoming concerts in san francisco through natural language commands.

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

The Composio search MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to the entire Composio Search suite. It provides structured and secure access to powerful web, travel, shopping, news, academic, and financial search tools, so your agent can perform actions like searching the web, finding events, locating places, pulling news, and fetching academic research on your behalf.

  • Comprehensive web and news search: Instantly ask your agent to fetch up-to-date web pages, breaking news, or current events using Google, DuckDuckGo, or news-specific search APIs.
  • Travel and local discovery: Let your agent find nearby hotels, flights, events, or map locations using Google Maps and events search for seamless travel planning and local exploration.
  • E-commerce and product lookup: Have your agent search for products, deals, and reviews across major retailers like Amazon and Walmart to help you shop smarter and faster.
  • Financial and market data retrieval: Direct your agent to pull real-time stock information, financial news, and market trends with just a query—no manual research needed.
  • Academic and scholarly research: Empower your agent to find relevant academic papers, citations, and scholarly articles using Google Scholar and Exa Answer for research-heavy tasks.

Supported Tools & Triggers

Tools
Composio DuckDuckGo SearchThe duckduckgosearch class utilizes the composio duckduckgo search api to perform searches, focusing on web information and details.
Composio Google Events SearchThe eventsearch class enables scraping of google events search queries.
Exa AnswerGet answers with citations using the exa api.
Composio SimilarlinksPerform a search to find similar links and retrieve a list of relevant results.
Composio Finance SearchThe financesearch class utilizes the composio finance search api to conduct financial searches, focusing on financial data and stock information.
Composio Google Maps SearchThe googlemapssearch class performs a location-specific search using the composio goolge maps search api.
Composio Image SearchThe imagesearch class performs an image search using the composio image search api, to target image data and information.
Composio News SearchThe newssearch class performs a news-specific search using the composio news search api.
Composio Scholar SearchScholar api allows you to scrape results from a google scholar search query.
Composio Google SearchPerform a google search using the composio google search api.
Composio Shopping SearchThe shoppingsearch class performs a product search using the composio shopping search api.
Composio LLM SearchThe composio llm search class serves as a gateway to the composio llm search api, allowing users to perform searches across a broad range of content with multiple filtering options.
Composio Trends SearchThe trendssearch class performs a trend search using the google trends search api, to target trend data and information.

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

How to build Composio search MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Composio search MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Composio search MCP with Claude Agent SDK

Google ADK

Google ADK

Use Composio search MCP with Google ADK

LangChain

LangChain

Use Composio search MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Composio search MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Composio search MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Composio search MCP with LlamaIndex

CrewAI

CrewAI

Use Composio search MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Composio search MCP?

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

Can I manage the permissions and scopes for Composio search while using Tool Router?

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

Used by agents from

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