SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Mocean MCP with Autogen

Connect Autogen to Mocean MCP. Send sms alert to a customer, deliver two-factor authentication code via sms, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Mocean logoMocean
Api Key

Mocean is a messaging platform providing SMS, voice, and verification APIs. It helps apps deliver secure messages and multifactor authentication without custom integrations.

6 Tools

Introduction

This guide walks you through connecting Mocean to AutoGen using the Composio tool router. By the end, you'll have a working Mocean agent that can send WhatsApp messages, check SMS status, place voice calls, download call recordings, and hang up calls through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Mocean with

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

The Mocean MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mocean account. It provides structured and secure access to your messaging and verification tools, so your agent can send SMS messages, initiate voice calls, manage two-factor authentication flows, and engage customers with real-time notifications on your behalf.

  • Automated SMS delivery: Instantly send text messages to users for alerts, notifications, or customer engagement with just a prompt to your agent.
  • Voice call automation: Instruct your agent to place voice calls for reminders, confirmations, or interactive customer communication flows.
  • Multi-factor authentication (MFA): Let your agent handle one-time password (OTP) generation and verification, streamlining secure user onboarding and login.
  • Two-way messaging management: Enable your agent to receive and process incoming SMS messages, supporting interactive conversations and quick customer responses.
  • Bulk campaign execution: Run large-scale SMS or voice campaigns through your agent, reaching many users simultaneously for marketing or transactional updates.

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

Supported Tools

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

Query SMS Message Status V2

Query an outbound SMS message's delivery status by message ID.

Voice Dial V2

Tool to initiate an outbound voice call via Mocean API.

Voice Download Recording V2

Download a call recording by call UUID.

Voice Hangup V2

Request hangup of an active voice call by call UUID.

WhatsApp Incoming Webhook V2

Validate and return a supplied incoming WhatsApp message webhook payload using the supported message schema.

WhatsApp Send Message V2

Send a WhatsApp message via Mocean, including text, media, template, reaction, or interactive content.

FRAMEWORKS

How to build Mocean MCP Agent with another framework

Claude Code logo

Claude Code

Use Mocean MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Mocean MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Mocean MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Mocean MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Mocean MCP with Grok Bot

Codex logo

Codex

Use Mocean MCP with Codex

OpenClaw logo

OpenClaw

Use Mocean MCP with OpenClaw

Hermes logo

Hermes

Use Mocean MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Mocean MCP with Atomic Agent

Google ADK logo

Google ADK

Use Mocean MCP with Google ADK

LangChain logo

LangChain

Use Mocean MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Mocean MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Mocean MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Mocean MCP with LlamaIndex

CrewAI logo

CrewAI

Use Mocean MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Mocean MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Mocean.It takes 30 seconds.

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

Start building