SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Botsonic MCP with Autogen

Connect Autogen to Botsonic MCP. List all bots in your account, export all conversation threads for review, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Botsonic logoBotsonic
Api Key

Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.

12 Tools

Introduction

This guide walks you through connecting Botsonic to AutoGen using the Composio tool router. By the end, you'll have a working Botsonic agent that can list your bots and conversations, manage starter questions, bulk upload training URLs, and browse FAQs through natural language commands.

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

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

Also integrate Botsonic with

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

The Botsonic MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Botsonic account. It provides structured and secure access to your chatbots, enabling your agent to manage bots, upload training data, oversee conversations, and handle FAQs with ease.

  • Bulk training data uploads: Effortlessly upload multiple URLs or documents to your bot for rapid and comprehensive training updates.
  • Bot management and retrieval: Instantly list all your bots, fetch detailed data, or export entire bot assets for backup or review.
  • Conversation analytics and monitoring: Retrieve all conversations related to any bot—perfect for analyzing user interactions or tracking support queries.
  • FAQ and starter question management: List, update, or remove FAQ entries and starter questions to keep your chatbot responses relevant and up to date.
  • Data and file cleanup: Direct your agent to delete outdated files or bot data, ensuring your chatbot remains efficient and well-organized.

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

Supported Tools

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

Bulk Upload Bot URLs

Tool to bulk upload URLs for bot training.

Create Starter Question

Tool to create a new starter question for the bot.

Delete Starter Question

Deletes a specific starter question from a bot using its unique identifier.

Delete Uploaded File

Delete an uploaded file or bot data entry by its unique identifier.

Get All Bot Data

Retrieve a paginated list of bot data records, including files and resources, with search and sorting options for inspection.

Get All Bots

Retrieve a paginated list of bots associated with your account, with search, sorting, and workspace filtering.

Get All Conversations

Tool to retrieve all conversations related to the bot.

Get All Conversations With Source

Tool to retrieve all conversations with source information.

Get All FAQs

Retrieve all frequently asked questions (FAQs) associated with your bot in paginated format.

Get All Starter Presets

Retrieve starter presets for the authenticated bot, including its welcome message and starter questions.

Get All Starter Questions

Tool to retrieve all starter questions.

Update Starter Question

Tool to update an existing starter question by its unique identifier.

FRAMEWORKS

How to build Botsonic MCP Agent with another framework

Claude Code logo

Claude Code

Use Botsonic MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Botsonic MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Botsonic MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Botsonic MCP with Claude Agent SDK

Codex logo

Codex

Use Botsonic MCP with Codex

OpenClaw logo

OpenClaw

Use Botsonic MCP with OpenClaw

Hermes logo

Hermes

Use Botsonic MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Botsonic MCP with Atomic Agent

Google ADK logo

Google ADK

Use Botsonic MCP with Google ADK

LangChain logo

LangChain

Use Botsonic MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Botsonic MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Botsonic MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Botsonic MCP with LlamaIndex

CrewAI logo

CrewAI

Use Botsonic MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Botsonic MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Botsonic.It takes 30 seconds.

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

Start building