How to integrate Ably MCP with Autogen

This guide walks you through connecting Ably to AutoGen using the Composio tool router. By the end, you'll have a working Ably agent that can list all active channels and their details, get message history from 'support-chat' channel, show presence history for 'live-event' channel through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Ably account through Composio's Ably 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
Ably logoAbly
Api Key

Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.

25 Tools

Introduction

This guide walks you through connecting Ably to AutoGen using the Composio tool router. By the end, you'll have a working Ably agent that can list all active channels and their details, get message history from 'support-chat' channel, show presence history for 'live-event' channel through natural language commands.

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

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

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

The Ably MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ably account. It provides structured and secure access to your real-time messaging infrastructure, so your agent can manage channels, monitor presence, analyze usage, and handle messaging workflows for your applications.

  • Channel management and creation: Seamlessly create, initialize, or retrieve real-time messaging channels so your agent can orchestrate chat, data sync, and collaboration features on demand.
  • Presence tracking and analytics: Ask your agent to query current presence states or review historical presence data across multiple channels, gaining insights into user activity and engagement patterns.
  • Message history and audit: Retrieve detailed message histories from any channel, enabling your agent to audit communication, recover missed messages, or analyze message flows for debugging and compliance.
  • Push notification subscription management: Let your agent list, manage, or unsubscribe devices from push notification channels, ensuring targeted and controlled delivery of real-time alerts to clients.
  • Application statistics and monitoring: Have your agent fetch in-depth usage metrics—like message counts, channel activity, and API request stats—so you can monitor health, optimize performance, and manage resources with confidence.

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

Supported Tools

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

Query Batch Presence

This tool enables querying the presence states of multiple channels in a single API request.

Query Batch Presence History

This tool enables querying presence history for multiple channels in a single API request.

Delete Channel Subscription

This tool allows you to unsubscribe devices or clients from push notifications for specific channels.

Get Channel Details

This tool retrieves metadata and details for a specific channel in Ably.

Get Channel History

This tool retrieves the message history for a specified Ably channel.

Get Channel Presence

Tool to obtain the set of members currently present for a channel.

Get Message Versions

Tool to retrieve all historical versions of a specific message from an Ably channel.

Get Channel Presence History

This tool retrieves the history of presence messages for a specified channel in Ably.

Get Push Device Registration

Tool to get the full details of a device registration for push notifications.

Get Ably Service Time

This tool retrieves the current server time from Ably's service in milliseconds since the epoch.

Get Application Stats

This tool retrieves your application's usage statistics from Ably.

List Channels

Tool to enumerate all active channels in the Ably application.

List Push Channels

Tool to list all channels with at least one subscribed device.

List Push Channel Subscriptions

This tool retrieves a list of all push notification channel subscriptions.

List Registered Push Devices

Tool to list all devices registered for receiving push notifications in your Ably application.

Patch Push Device Registration

Tool to partially update specific attributes of an existing device registration in Ably's push notification system.

Batch Publish Messages

Tool to batch publish messages to multiple channels in parallel.

Publish Message to Channel

This tool will allow users to publish a message to a specified Ably channel using a POST request.

Publish Push Notification

Tool to publish a push notification directly to device(s) via Ably's Push Notifications API.

Batch Publish Push Notifications

Tool to batch publish push notifications directly to specific recipients.

Register Push Device

Tool to register a device for receiving push notifications in Ably.

Request Access Token

Request an access token for Ably authentication.

Unregister All Push Devices

Tool to unregister matching devices for push notifications.

Unregister Push Device

Tool to unregister a single device from push notifications in Ably.

Update Push Device Registration

Tool to update (upsert) a device registration for push notifications in Ably.

FRAMEWORKS

How to build Ably MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Ably MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Ably MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Ably MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Ably MCP with Claude Cowork

Codex logo

Codex

Use Ably MCP with Codex

OpenClaw logo

OpenClaw

Use Ably MCP with OpenClaw

Hermes logo

Hermes

Use Ably MCP with Hermes

CLI logo

CLI

Use Ably MCP with CLI

Google ADK logo

Google ADK

Use Ably MCP with Google ADK

LangChain logo

LangChain

Use Ably MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Ably MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Ably MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Ably MCP with LlamaIndex

CrewAI logo

CrewAI

Use Ably MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Ably.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Ably 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