SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Sendfox MCP with Autogen

Connect Autogen to Sendfox MCP. List all active campaigns this week, unsubscribe a contact by email address, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Sendfox logoSendfox
Api Key

Sendfox is an email marketing platform focused on simple, affordable campaign management for creators and small businesses. It lets you grow and engage your audience with automated newsletters and easy contact organization.

17 Tools

Introduction

This guide walks you through connecting Sendfox to AutoGen using the Composio tool router. By the end, you'll have a working Sendfox agent that can create contacts and lists, unsubscribe contacts, review campaigns and automations, browse forms, and manage contact fields through natural language commands.

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

The Sendfox MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Sendfox account. It provides structured and secure access to your contact lists, campaigns, automations, and more, so your agent can fetch contacts, manage lists, retrieve campaign data, and automate subscriber actions on your behalf.

  • Contact management and lookup: Instantly retrieve contact details by email or ID, fetch all contacts, or discover specific fields to personalize your outreach.
  • List organization and updates: Ask your agent to fetch all your Sendfox lists, get details for a specific list, or remove contacts from lists as needed.
  • Campaign and automation insights: Effortlessly retrieve paginated lists of campaigns or automations, so you can stay on top of your email marketing performance.
  • Subscription and unsubscribe actions: Let your agent globally unsubscribe a contact or handle opt-outs automatically for better list hygiene.
  • Discover contact field metadata: Pull all available contact fields to help with dynamic contact creation or targeted 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 Sendfox 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 Sendfox 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 Sendfox 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 Sendfox session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["sendfox"]
    )
    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 Sendfox 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 Sendfox assistant agent with MCP tools
    agent = AssistantAgent(
        name="sendfox_assistant",
        description="An AI assistant that helps with Sendfox 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 Sendfox 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 Sendfox 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 Sendfox 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 Sendfox 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 Sendfox session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["sendfox"]
    )
    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 Sendfox assistant agent with MCP tools
        agent = AssistantAgent(
            name="sendfox_assistant",
            description="An AI assistant that helps with Sendfox 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 Sendfox 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 Sendfox 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 Sendfox, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Delete Contact from List

Tool to remove a contact from a specific list in SendFox.

Get Automations

Retrieve automations from the SendFox account.

Get Campaign by ID

Retrieve details for a specific campaign by its ID from SendFox.

Get Campaigns

Retrieve a page of SendFox email campaigns, with subject and timestamps when provided.

Get Contact by ID

Retrieves a contact's details by their unique ID from SendFox.

Get Contact Fields

Retrieve contact fields from SendFox.

Get Contacts

Tool to retrieve a paginated list of contacts.

Get Contacts in List

Retrieve a page of contacts belonging to a specific list, optionally filtering by search query.

Get Current User

Retrieve information about the authenticated SendFox user, including name and email.

Get Forms

Retrieve a page of SendFox forms, optionally searching by query.

Get List by ID

Retrieves details of a specific contact list by its ID from SendFox.

Get Lists

Retrieve all contact lists from your SendFox account with pagination support.

List Contact Fields

Retrieve a page of the user's custom contact fields, including their IDs, labels, names, and types.

List Unsubscribed Contacts

Retrieve a paginated list of unsubscribed contacts, optionally filtered by search query.

Unsubscribe Contact

Unsubscribe a contact from all email communications in your SendFox account.

Create Contact

Create a new contact (subscriber) in your SendFox account.

Create List

Create a new contact list in your SendFox account.

FRAMEWORKS

How to build Sendfox MCP Agent with another framework

Claude Code logo

Claude Code

Use Sendfox MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Sendfox MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Sendfox MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Sendfox MCP with Claude Agent SDK

Codex logo

Codex

Use Sendfox MCP with Codex

OpenClaw logo

OpenClaw

Use Sendfox MCP with OpenClaw

Hermes logo

Hermes

Use Sendfox MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Sendfox MCP with Atomic Agent

Google ADK logo

Google ADK

Use Sendfox MCP with Google ADK

LangChain logo

LangChain

Use Sendfox MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Sendfox MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Sendfox MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Sendfox MCP with LlamaIndex

CrewAI logo

CrewAI

Use Sendfox MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Sendfox MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Sendfox.It takes 30 seconds.

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

Start building