How to integrate Sendbird ai chabot MCP with Autogen

GET STARTED FOR FREE
Sendbird ai chabot logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Sendbird ai chabot to AutoGen using the Composio tool router. By the end, you'll have a working Sendbird ai chabot agent that can list all group channels for support, create a new chatbot for onboarding, update bot nickname to match rebranding through natural language commands.

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

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

Also integrate Sendbird ai chabot with

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

The Sendbird ai chabot MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Sendbird ai chabot account. It provides structured and secure access to your Sendbird bots and channels, so your agent can create bots, manage webhooks, update bot profiles, and fetch group channel details seamlessly on your behalf.

  • Bot creation and management: Easily instruct your agent to create new AI or default bots, update their profiles, or fetch detailed bot information as needed.
  • Automated webhook management: Let your agent register, update, or remove webhook URLs for bots, ensuring seamless event-driven integrations and real-time notifications.
  • Group channel discovery: Ask your agent to list available group channels in your Sendbird application, complete with filtering and pagination support for targeted results.
  • Bot information retrieval: Have your agent fetch comprehensive details about any bot by its user ID, helping you monitor and audit bot activity at a glance.
  • Bot privacy and feature updates: Direct your agent to toggle privacy settings or adjust read-receipt and webhook configurations, keeping your bots up to date with business needs.

Supported Tools & Triggers

Tools
Create BotTool to create a new bot.
Get BotTool to retrieve information on a specific bot by its user id.
List BotsTool to list all bots in the sendbird application.
List Group ChannelsTool to list group channels.
Unregister Bot WebhookTool to unregister the webhook url for a bot.
Update BotTool to update information on an existing bot.
Update Bot WebhookTool to update the webhook url of an existing bot.

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

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["sendbird_ai_chabot"]
    )
    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 Sendbird ai chabot 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 Sendbird ai chabot assistant agent with MCP tools
    agent = AssistantAgent(
        name="sendbird_ai_chabot_assistant",
        description="An AI assistant that helps with Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["sendbird_ai_chabot"]
    )
    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 Sendbird ai chabot assistant agent with MCP tools
        agent = AssistantAgent(
            name="sendbird_ai_chabot_assistant",
            description="An AI assistant that helps with Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot 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 Sendbird ai chabot, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Sendbird ai chabot MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Sendbird ai chabot MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Sendbird ai chabot MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Sendbird ai chabot MCP with Claude Code

Codex logo

Codex

Use Sendbird ai chabot MCP with Codex

OpenClaw logo

OpenClaw

Use Sendbird ai chabot MCP with OpenClaw

CLI logo

CLI

Use Sendbird ai chabot MCP with CLI

Google ADK logo

Google ADK

Use Sendbird ai chabot MCP with Google ADK

LangChain logo

LangChain

Use Sendbird ai chabot MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Sendbird ai chabot MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Sendbird ai chabot MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Sendbird ai chabot MCP with LlamaIndex

CrewAI logo

CrewAI

Use Sendbird ai chabot MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Sendbird ai chabot MCP?

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

Can I manage the permissions and scopes for Sendbird ai chabot while using Tool Router?

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

Used by agents from

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